{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/dataset/kitti-360","name":"KITTI-360","full_name":null,"description_markdown":"KITTI-360 is a large-scale dataset that contains rich sensory information and full annotations. It is the successor of the popular KITTI dataset,  providing more comprehensive semantic/instance labels in 2D and 3D, richer 360 degree sensory information (fisheye images and pushbroom laser scans), very accurate and geo-localized vehicle and camera poses, and a series of new challenging benchmarks.","description_withheld":null,"homepage":"http://www.cvlibs.net/datasets/kitti-360/","introduced_date":"2021-09-28","introduced_date_note":null,"introduced_by":{"paper":"/paper/kitti-360-a-novel-dataset-and-benchmarks-for","title":"KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D","first_author":"Yiyi Liao","url":null},"license":{"name":"All datasets and benchmarks on this page are copyright by us and published under the Creative Commons Attribution-NonCommercial-ShareAlike 3.0 License. This means that you must attribute the work in the manner specified by the authors, you may not use this work for commercial purposes and if you alter, transform, or build upon this work, you may distribute the resulting work only under the same license. Per GDPR requirements, to download and to use the data you need to register and specify the i","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"LiDAR","url":"/datasets/modality/lidar"}],"tasks":[{"name":"Semantic Segmentation","url":"/task/semantic-segmentation","datasets_with_task":"/datasets/task/semantic-segmentation"},{"name":"2D Semantic Segmentation","url":"/task/2d-semantic-segmentation","datasets_with_task":"/datasets/task/2d-semantic-segmentation"},{"name":"Instance Segmentation","url":"/task/instance-segmentation","datasets_with_task":"/datasets/task/instance-segmentation"},{"name":"Panoptic Segmentation","url":"/task/panoptic-segmentation","datasets_with_task":"/datasets/task/panoptic-segmentation"},{"name":"Novel View Synthesis","url":"/task/novel-view-synthesis","datasets_with_task":"/datasets/task/novel-view-synthesis"},{"name":"3D Semantic Segmentation","url":"/task/3d-semantic-segmentation","datasets_with_task":"/datasets/task/3d-semantic-segmentation"},{"name":"3D Instance Segmentation","url":"/task/3d-instance-segmentation-1","datasets_with_task":"/datasets/task/3d-instance-segmentation-1"},{"name":"3D Semantic Scene Completion","url":"/task/3d-semantic-scene-completion","datasets_with_task":"/datasets/task/3d-semantic-scene-completion"},{"name":"3D Object Detection From Monocular Images","url":"/task/3d-object-detection-from-monocular-images","datasets_with_task":"/datasets/task/3d-object-detection-from-monocular-images"},{"name":"3D Semantic Scene Completion from a single RGB image","url":"/task/3d-semantic-scene-completion-from-a-single","datasets_with_task":"/datasets/task/3d-semantic-scene-completion-from-a-single"},{"name":"Semantic SLAM","url":"/task/semantic-slam","datasets_with_task":"/datasets/task/semantic-slam"},{"name":"Weakly Supervised 3D Detection","url":"/task/weakly-supervised-3d-detection","datasets_with_task":"/datasets/task/weakly-supervised-3d-detection"}],"languages":[],"variants":["KITTI-360"],"data_loaders":[],"num_papers_in_archive":246,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/semantic-segmentation-on-kitti-360","task":"Semantic Segmentation","dataset_variant":"KITTI-360","rows":17,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"DiPFormer","paper":"/paper/depth-matters-exploring-deep-interactions-of","metrics":{"mIoU":"68.74"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/3d-object-detection-from-monocular-images-on-7","task":"3D Object Detection From Monocular Images","dataset_variant":"KITTI-360","rows":11,"metrics":["AP50","AP25"],"first_row_in_archive_order":{"model":"SeaBird + PanopticBEV","paper":"/paper/seabird-segmentation-in-bird-s-view-with-dice","metrics":{"AP25":"37.12","AP50":"4.64"},"code_links":[{"title":"abhi1kumar/seabird","url":"https://github.com/abhi1kumar/seabird"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/3d-semantic-segmentation-on-kitti-360","task":"3D Semantic Segmentation","dataset_variant":"KITTI-360","rows":8,"metrics":["miou","mIoU Category","miou Val","Model size"],"first_row_in_archive_order":{"model":"DeepViewAgg","paper":"/paper/learning-multi-view-aggregation-in-the-wild","metrics":{"Model size":"41.2M","mIoU Category":"73.66","miou":"58.3","miou Val":"57.8"},"code_links":[{"title":"drprojects/deepviewagg","url":"https://github.com/drprojects/deepviewagg"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/3d-semantic-scene-completion-on-kitti-360","task":"3D Semantic Scene Completion","dataset_variant":"KITTI-360","rows":7,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"Symphonies","paper":"/paper/symphonize-3d-semantic-scene-completion-with","metrics":{"mIoU":"18.58"},"code_links":[{"title":"hustvl/symphonies","url":"https://github.com/hustvl/symphonies"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/3d-semantic-scene-completion-from-a-single-2","task":"3D Semantic Scene Completion from a single RGB image","dataset_variant":"KITTI-360","rows":4,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"CGFormer","paper":"/paper/context-and-geometry-aware-voxel-transformer","metrics":{"mIoU":"20.05"},"code_links":[{"title":"pkqbajng/cgformer","url":"https://github.com/pkqbajng/cgformer"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/weakly-supervised-3d-detection-on-kitti-360","task":"Weakly Supervised 3D Detection","dataset_variant":"KITTI-360","rows":3,"metrics":["mAP@0.3"],"first_row_in_archive_order":{"model":"VSRD-MonoDETR","paper":"/paper/vsrd-instance-aware-volumetric-silhouette-1","metrics":{"mAP@0.3":"58.40"},"code_links":[{"title":"skmhrk1209/VSRD","url":"https://github.com/skmhrk1209/VSRD"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/panoptic-segmentation-on-kitti-360","task":"Panoptic Segmentation","dataset_variant":"KITTI-360","rows":1,"metrics":["PQ","RQ","SQ","Params (M)"],"first_row_in_archive_order":{"model":"SuperCluster","paper":"/paper/scalable-3d-panoptic-segmentation-with","metrics":{"PQ":"48.3","Params (M)":"0.79","RQ":"58.4","SQ":"75.1"},"code_links":[{"title":"drprojects/superpoint_transformer","url":"https://github.com/drprojects/superpoint_transformer"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":37,"of":37,"counts":{"papers_with_a_benchmark_row":37,"with_a_code_link":35,"where_syntology_ran_a_sample":20,"not_listed_spam_title":0,"listed":37,"listed_where_code_ran":20,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":16,"every_run_a_failure_of_syntologys_instrument":4,"listed_with_a_run_with_no_instrument_failure":16,"listed_every_run_a_failure_of_syntologys_instrument":4,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/hspformer-hierarchical-spatial-perception","slug":"hspformer-hierarchical-spatial-perception","title":"HSPFormer: Hierarchical Spatial Perception Transformer for Semantic Segmentation","date":"2025-01-16","arxiv_id":null,"rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/cloudspam-contrastive-learning-on-unlabeled","slug":"cloudspam-contrastive-learning-on-unlabeled","title":"CLOUDSPAM: Contrastive Learning On Unlabeled Data for Segmentation and Pre-Training Using Aggregated Point Clouds and MoCo","date":"2024-10-26","arxiv_id":null,"rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/depth-matters-exploring-deep-interactions-of","slug":"depth-matters-exploring-deep-interactions-of","title":"Depth Matters: Exploring Deep Interactions of RGB-D for Semantic Segmentation in Traffic Scenes","date":"2024-09-12","arxiv_id":"2409.07995","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/context-and-geometry-aware-voxel-transformer","slug":"context-and-geometry-aware-voxel-transformer","title":"Context and Geometry Aware Voxel Transformer for Semantic Scene Completion","date":"2024-05-22","arxiv_id":"2405.13675","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["pkqbajng/cgformer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/context-and-geometry-aware-voxel-transformer#ran","syntology_url":"https://syntology.ai/paper/2405.13675","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.13675"}}}},{"paper":"/paper/seabird-segmentation-in-bird-s-view-with-dice","slug":"seabird-segmentation-in-bird-s-view-with-dice","title":"SeaBird: Segmentation in Bird's View with Dice Loss Improves Monocular 3D Detection of Large Objects","date":"2024-03-29","arxiv_id":"2403.20318","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/vsrd-instance-aware-volumetric-silhouette-1","slug":"vsrd-instance-aware-volumetric-silhouette-1","title":"VSRD: Instance-Aware Volumetric Silhouette Rendering for Weakly Supervised 3D Object Detection","date":"2024-03-29","arxiv_id":"2404.00149","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["skmhrk1209/VSRD"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vsrd-instance-aware-volumetric-silhouette-1#ran","syntology_url":"https://syntology.ai/paper/2404.00149","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.00149"}}}},{"paper":"/paper/scalable-3d-panoptic-segmentation-with","slug":"scalable-3d-panoptic-segmentation-with","title":"Scalable 3D Panoptic Segmentation As Superpoint Graph Clustering","date":"2024-01-12","arxiv_id":"2401.06704","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/symphonize-3d-semantic-scene-completion-with","slug":"symphonize-3d-semantic-scene-completion-with","title":"Symphonize 3D Semantic Scene Completion with Contextual Instance Queries","date":"2023-06-27","arxiv_id":"2306.15670","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":5,"samples_unverified":1,"pointer_only_for_licence":2,"official":{"repos":["hustvl/symphonies"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/symphonize-3d-semantic-scene-completion-with#ran","syntology_url":"https://syntology.ai/paper/2306.15670","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.15670"}}}},{"paper":"/paper/efficient-3d-semantic-segmentation-with-1","slug":"efficient-3d-semantic-segmentation-with-1","title":"Efficient 3D Semantic Segmentation with Superpoint Transformer","date":"2023-06-13","arxiv_id":"2306.08045","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/occformer-dual-path-transformer-for-vision","slug":"occformer-dual-path-transformer-for-vision","title":"OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction","date":"2023-04-11","arxiv_id":"2304.05316","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["zhangyp15/occformer"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/occformer-dual-path-transformer-for-vision#ran","syntology_url":"https://syntology.ai/paper/2304.05316","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.05316"}}}},{"paper":"/paper/delivering-arbitrary-modal-semantic","slug":"delivering-arbitrary-modal-semantic","title":"Delivering Arbitrary-Modal Semantic Segmentation","date":"2023-03-02","arxiv_id":"2303.01480","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":6,"official":{"repos":["jamycheung/DELIVER"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/delivering-arbitrary-modal-semantic#ran","syntology_url":"https://syntology.ai/paper/2303.01480","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.01480"}}}},{"paper":"/paper/voxformer-sparse-voxel-transformer-for-camera","slug":"voxformer-sparse-voxel-transformer-for-camera","title":"VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion","date":"2023-02-23","arxiv_id":"2302.12251","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/tri-perspective-view-for-vision-based-3d","slug":"tri-perspective-view-for-vision-based-3d","title":"Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction","date":"2023-02-15","arxiv_id":"2302.07817","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["wzzheng/tpvformer"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/tri-perspective-view-for-vision-based-3d#ran","syntology_url":"https://syntology.ai/paper/2302.07817","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.07817"}}}},{"paper":"/paper/deviant-depth-equivariant-network-for","slug":"deviant-depth-equivariant-network-for","title":"DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detection","date":"2022-07-21","arxiv_id":"2207.10758","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":9,"samples_constructed":3,"samples_ran_checked":7,"samples_ran_instrument_failed":2,"samples_unverified":6,"pointer_only_for_licence":0,"official":{"repos":["abhi1kumar/deviant"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/deviant-depth-equivariant-network-for#ran","syntology_url":"https://syntology.ai/paper/2207.10758","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.10758"}}}},{"paper":"/paper/omni3d-a-large-benchmark-and-model-for-3d","slug":"omni3d-a-large-benchmark-and-model-for-3d","title":"Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild","date":"2022-07-21","arxiv_id":"2207.10660","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/hrfuser-a-multi-resolution-sensor-fusion","slug":"hrfuser-a-multi-resolution-sensor-fusion","title":"HRFuser: A Multi-resolution Sensor Fusion Architecture for 2D Object Detection","date":"2022-06-30","arxiv_id":"2206.15157","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/multimodal-token-fusion-for-vision","slug":"multimodal-token-fusion-for-vision","title":"Multimodal Token Fusion for Vision Transformers","date":"2022-04-19","arxiv_id":"2204.08721","rows_on_this_dataset":2,"code_links":11,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["yikaiw/TokenFusion","huawei-noah/noah-research","mindspore-ai/models"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/multimodal-token-fusion-for-vision#ran","syntology_url":"https://syntology.ai/paper/2204.08721","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.08721"}}}},{"paper":"/paper/learning-multi-view-aggregation-in-the-wild","slug":"learning-multi-view-aggregation-in-the-wild","title":"Learning Multi-View Aggregation In the Wild for Large-Scale 3D Semantic Segmentation","date":"2022-04-15","arxiv_id":"2204.07548","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/monodetr-depth-aware-transformer-for","slug":"monodetr-depth-aware-transformer-for","title":"MonoDETR: Depth-guided Transformer for Monocular 3D Object Detection","date":"2022-03-24","arxiv_id":"2203.13310","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/monodtr-monocular-3d-object-detection-with","slug":"monodtr-monocular-3d-object-detection-with","title":"MonoDTR: Monocular 3D Object Detection with Depth-Aware Transformer","date":"2022-03-21","arxiv_id":"2203.10981","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["kuanchihhuang/monodtr"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/monodtr-monocular-3d-object-detection-with#ran","syntology_url":"https://syntology.ai/paper/2203.10981","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.10981"}}}},{"paper":"/paper/weakm3d-towards-weakly-supervised-monocular-1","slug":"weakm3d-towards-weakly-supervised-monocular-1","title":"WeakM3D: Towards Weakly Supervised Monocular 3D Object Detection","date":"2022-03-16","arxiv_id":"2203.08332","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":3,"official":{"repos":["spengliang/weakm3d"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/weakm3d-towards-weakly-supervised-monocular-1#ran","syntology_url":"https://syntology.ai/paper/2203.08332","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.08332"}}}},{"paper":"/paper/cmx-cross-modal-fusion-for-rgb-x-semantic","slug":"cmx-cross-modal-fusion-for-rgb-x-semantic","title":"CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers","date":"2022-03-09","arxiv_id":"2203.04838","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["huaaaliu/rgbx_semantic_segmentation"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/cmx-cross-modal-fusion-for-rgb-x-semantic#ran","syntology_url":"https://syntology.ai/paper/2203.04838","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.04838"}}}},{"paper":"/paper/glass-segmentation-using-intensity-and","slug":"glass-segmentation-using-intensity-and","title":"Glass Segmentation Using Intensity and Spectral Polarization Cues","date":"2022-01-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/monoscene-monocular-3d-semantic-scene","slug":"monoscene-monocular-3d-semantic-scene","title":"MonoScene: Monocular 3D Semantic Scene Completion","date":"2021-12-01","arxiv_id":"2112.00726","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":2,"official":{"repos":["cv-rits/MonoScene"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/monoscene-monocular-3d-semantic-scene#ran","syntology_url":"https://syntology.ai/paper/2112.00726","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.00726"}}}},{"paper":"/paper/geometry-uncertainty-projection-network-for","slug":"geometry-uncertainty-projection-network-for","title":"Geometry Uncertainty Projection Network for Monocular 3D Object Detection","date":"2021-07-29","arxiv_id":"2107.13774","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":21,"samples_ran":16,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":6,"samples_unverified":5,"pointer_only_for_licence":2,"official":{"repos":["supermhp/gupnet"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":5,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/geometry-uncertainty-projection-network-for#ran","syntology_url":"https://syntology.ai/paper/2107.13774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.13774"}}}},{"paper":"/paper/perception-aware-multi-sensor-fusion-for-3d","slug":"perception-aware-multi-sensor-fusion-for-3d","title":"EPMF: Efficient Perception-aware Multi-sensor Fusion for 3D Semantic Segmentation","date":"2021-06-21","arxiv_id":"2106.15277","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/multi-modal-fusion-transformer-for-end-to-end","slug":"multi-modal-fusion-transformer-for-end-to-end","title":"Multi-Modal Fusion Transformer for End-to-End Autonomous Driving","date":"2021-04-19","arxiv_id":"2104.09224","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":9,"samples_constructed":7,"samples_ran_checked":8,"samples_ran_instrument_failed":1,"samples_unverified":6,"pointer_only_for_licence":0,"official":{"repos":["autonomousvision/transfuser"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/multi-modal-fusion-transformer-for-end-to-end#ran","syntology_url":"https://syntology.ai/paper/2104.09224","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.09224"}}}},{"paper":"/paper/groomed-nms-grouped-mathematically","slug":"groomed-nms-grouped-mathematically","title":"GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection","date":"2021-03-31","arxiv_id":"2103.17202","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":4,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["abhi1kumar/groomed_nms"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/groomed-nms-grouped-mathematically#ran","syntology_url":"https://syntology.ai/paper/2103.17202","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.17202"}}}},{"paper":"/paper/delving-into-localization-errors-for","slug":"delving-into-localization-errors-for","title":"Delving into Localization Errors for Monocular 3D Object Detection","date":"2021-03-30","arxiv_id":"2103.16237","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["xinzhuma/monodle"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/delving-into-localization-errors-for#ran","syntology_url":"https://syntology.ai/paper/2103.16237","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.16237"}}}},{"paper":"/paper/lmscnet-lightweight-multiscale-3d-semantic","slug":"lmscnet-lightweight-multiscale-3d-semantic","title":"LMSCNet: Lightweight Multiscale 3D Semantic Completion","date":"2020-08-24","arxiv_id":"2008.10559","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/issafe-improving-semantic-segmentation-in","slug":"issafe-improving-semantic-segmentation-in","title":"ISSAFE: Improving Semantic Segmentation in Accidents by Fusing Event-based Data","date":"2020-08-20","arxiv_id":"2008.08974","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/autolabeling-3d-objects-with-differentiable","slug":"autolabeling-3d-objects-with-differentiable","title":"Autolabeling 3D Objects with Differentiable Rendering of SDF Shape Priors","date":"2019-11-26","arxiv_id":"1911.11288","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["TRI-ML/sdflabel"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/autolabeling-3d-objects-with-differentiable#ran","syntology_url":"https://syntology.ai/paper/1911.11288","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.11288"}}}},{"paper":"/paper/acnet-attention-based-network-to-exploit","slug":"acnet-attention-based-network-to-exploit","title":"ACNet: Attention Based Network to Exploit Complementary Features for RGBD Semantic Segmentation","date":"2019-05-24","arxiv_id":"1905.10089","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/deep-hough-voting-for-3d-object-detection-in","slug":"deep-hough-voting-for-3d-object-detection-in","title":"Deep Hough Voting for 3D Object Detection in Point Clouds","date":"2019-04-21","arxiv_id":"1904.09664","rows_on_this_dataset":2,"code_links":13,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":2,"samples_unverified":2,"pointer_only_for_licence":10,"official":{"repos":["facebookresearch/votenet"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/deep-hough-voting-for-3d-object-detection-in#ran","syntology_url":"https://syntology.ai/paper/1904.09664","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.09664"}}}},{"paper":"/paper/pointnet-deep-hierarchical-feature-learning","slug":"pointnet-deep-hierarchical-feature-learning","title":"PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space","date":"2017-06-07","arxiv_id":"1706.02413","rows_on_this_dataset":1,"code_links":68,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":67,"samples_ran":36,"samples_constructed":31,"samples_ran_checked":33,"samples_ran_instrument_failed":3,"samples_unverified":31,"pointer_only_for_licence":26,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/pointnet-deep-hierarchical-feature-learning#ran","syntology_url":"https://syntology.ai/paper/1706.02413","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1706.02413"}}}},{"paper":"/paper/pointnet-deep-learning-on-point-sets-for-3d","slug":"pointnet-deep-learning-on-point-sets-for-3d","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","date":"2016-12-02","arxiv_id":"1612.00593","rows_on_this_dataset":1,"code_links":110,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":164,"samples_ran":103,"samples_constructed":45,"samples_ran_checked":74,"samples_ran_instrument_failed":29,"samples_unverified":61,"pointer_only_for_licence":92,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/pointnet-deep-learning-on-point-sets-for-3d#ran","syntology_url":"https://syntology.ai/paper/1612.00593","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1612.00593"}}}},{"paper":"/paper/semantic-scene-completion-from-a-single-depth","slug":"semantic-scene-completion-from-a-single-depth","title":"Semantic Scene Completion from a Single Depth Image","date":"2016-11-28","arxiv_id":"1611.08974","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["shurans/sscnet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/semantic-scene-completion-from-a-single-depth#ran","syntology_url":"https://syntology.ai/paper/1611.08974","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.08974"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/hspformer-hierarchical-spatial-perception","slug":"hspformer-hierarchical-spatial-perception","title":"HSPFormer: Hierarchical Spatial Perception Transformer for Semantic Segmentation","date":"2025-01-16","arxiv_id":null,"rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/cloudspam-contrastive-learning-on-unlabeled","slug":"cloudspam-contrastive-learning-on-unlabeled","title":"CLOUDSPAM: Contrastive Learning On Unlabeled Data for Segmentation and Pre-Training Using Aggregated Point Clouds and MoCo","date":"2024-10-26","arxiv_id":null,"rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/depth-matters-exploring-deep-interactions-of","slug":"depth-matters-exploring-deep-interactions-of","title":"Depth Matters: Exploring Deep Interactions of RGB-D for Semantic Segmentation in Traffic Scenes","date":"2024-09-12","arxiv_id":"2409.07995","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/context-and-geometry-aware-voxel-transformer","slug":"context-and-geometry-aware-voxel-transformer","title":"Context and Geometry Aware Voxel Transformer for Semantic Scene Completion","date":"2024-05-22","arxiv_id":"2405.13675","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["pkqbajng/cgformer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/context-and-geometry-aware-voxel-transformer#ran","syntology_url":"https://syntology.ai/paper/2405.13675","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.13675"}}}},{"paper":"/paper/seabird-segmentation-in-bird-s-view-with-dice","slug":"seabird-segmentation-in-bird-s-view-with-dice","title":"SeaBird: Segmentation in Bird's View with Dice Loss Improves Monocular 3D Detection of Large Objects","date":"2024-03-29","arxiv_id":"2403.20318","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/vsrd-instance-aware-volumetric-silhouette-1","slug":"vsrd-instance-aware-volumetric-silhouette-1","title":"VSRD: Instance-Aware Volumetric Silhouette Rendering for Weakly Supervised 3D Object Detection","date":"2024-03-29","arxiv_id":"2404.00149","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["skmhrk1209/VSRD"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vsrd-instance-aware-volumetric-silhouette-1#ran","syntology_url":"https://syntology.ai/paper/2404.00149","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.00149"}}}},{"paper":"/paper/scalable-3d-panoptic-segmentation-with","slug":"scalable-3d-panoptic-segmentation-with","title":"Scalable 3D Panoptic Segmentation As Superpoint Graph Clustering","date":"2024-01-12","arxiv_id":"2401.06704","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/symphonize-3d-semantic-scene-completion-with","slug":"symphonize-3d-semantic-scene-completion-with","title":"Symphonize 3D Semantic Scene Completion with Contextual Instance Queries","date":"2023-06-27","arxiv_id":"2306.15670","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":5,"samples_unverified":1,"pointer_only_for_licence":2,"official":{"repos":["hustvl/symphonies"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/symphonize-3d-semantic-scene-completion-with#ran","syntology_url":"https://syntology.ai/paper/2306.15670","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.15670"}}}},{"paper":"/paper/efficient-3d-semantic-segmentation-with-1","slug":"efficient-3d-semantic-segmentation-with-1","title":"Efficient 3D Semantic Segmentation with Superpoint Transformer","date":"2023-06-13","arxiv_id":"2306.08045","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/occformer-dual-path-transformer-for-vision","slug":"occformer-dual-path-transformer-for-vision","title":"OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction","date":"2023-04-11","arxiv_id":"2304.05316","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["zhangyp15/occformer"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/occformer-dual-path-transformer-for-vision#ran","syntology_url":"https://syntology.ai/paper/2304.05316","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.05316"}}}},{"paper":"/paper/delivering-arbitrary-modal-semantic","slug":"delivering-arbitrary-modal-semantic","title":"Delivering Arbitrary-Modal Semantic Segmentation","date":"2023-03-02","arxiv_id":"2303.01480","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":6,"official":{"repos":["jamycheung/DELIVER"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/delivering-arbitrary-modal-semantic#ran","syntology_url":"https://syntology.ai/paper/2303.01480","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.01480"}}}},{"paper":"/paper/voxformer-sparse-voxel-transformer-for-camera","slug":"voxformer-sparse-voxel-transformer-for-camera","title":"VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion","date":"2023-02-23","arxiv_id":"2302.12251","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/tri-perspective-view-for-vision-based-3d","slug":"tri-perspective-view-for-vision-based-3d","title":"Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction","date":"2023-02-15","arxiv_id":"2302.07817","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["wzzheng/tpvformer"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/tri-perspective-view-for-vision-based-3d#ran","syntology_url":"https://syntology.ai/paper/2302.07817","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.07817"}}}},{"paper":"/paper/deviant-depth-equivariant-network-for","slug":"deviant-depth-equivariant-network-for","title":"DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detection","date":"2022-07-21","arxiv_id":"2207.10758","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":9,"samples_constructed":3,"samples_ran_checked":7,"samples_ran_instrument_failed":2,"samples_unverified":6,"pointer_only_for_licence":0,"official":{"repos":["abhi1kumar/deviant"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/deviant-depth-equivariant-network-for#ran","syntology_url":"https://syntology.ai/paper/2207.10758","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.10758"}}}},{"paper":"/paper/omni3d-a-large-benchmark-and-model-for-3d","slug":"omni3d-a-large-benchmark-and-model-for-3d","title":"Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild","date":"2022-07-21","arxiv_id":"2207.10660","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/hrfuser-a-multi-resolution-sensor-fusion","slug":"hrfuser-a-multi-resolution-sensor-fusion","title":"HRFuser: A Multi-resolution Sensor Fusion Architecture for 2D Object Detection","date":"2022-06-30","arxiv_id":"2206.15157","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/multimodal-token-fusion-for-vision","slug":"multimodal-token-fusion-for-vision","title":"Multimodal Token Fusion for Vision Transformers","date":"2022-04-19","arxiv_id":"2204.08721","rows_on_this_dataset":2,"code_links":11,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["yikaiw/TokenFusion","huawei-noah/noah-research","mindspore-ai/models"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/multimodal-token-fusion-for-vision#ran","syntology_url":"https://syntology.ai/paper/2204.08721","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.08721"}}}},{"paper":"/paper/learning-multi-view-aggregation-in-the-wild","slug":"learning-multi-view-aggregation-in-the-wild","title":"Learning Multi-View Aggregation In the Wild for Large-Scale 3D Semantic Segmentation","date":"2022-04-15","arxiv_id":"2204.07548","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/monodetr-depth-aware-transformer-for","slug":"monodetr-depth-aware-transformer-for","title":"MonoDETR: Depth-guided Transformer for Monocular 3D Object Detection","date":"2022-03-24","arxiv_id":"2203.13310","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/monodtr-monocular-3d-object-detection-with","slug":"monodtr-monocular-3d-object-detection-with","title":"MonoDTR: Monocular 3D Object Detection with Depth-Aware Transformer","date":"2022-03-21","arxiv_id":"2203.10981","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["kuanchihhuang/monodtr"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/monodtr-monocular-3d-object-detection-with#ran","syntology_url":"https://syntology.ai/paper/2203.10981","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.10981"}}}},{"paper":"/paper/weakm3d-towards-weakly-supervised-monocular-1","slug":"weakm3d-towards-weakly-supervised-monocular-1","title":"WeakM3D: Towards Weakly Supervised Monocular 3D Object Detection","date":"2022-03-16","arxiv_id":"2203.08332","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":3,"official":{"repos":["spengliang/weakm3d"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/weakm3d-towards-weakly-supervised-monocular-1#ran","syntology_url":"https://syntology.ai/paper/2203.08332","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.08332"}}}},{"paper":"/paper/cmx-cross-modal-fusion-for-rgb-x-semantic","slug":"cmx-cross-modal-fusion-for-rgb-x-semantic","title":"CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers","date":"2022-03-09","arxiv_id":"2203.04838","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["huaaaliu/rgbx_semantic_segmentation"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/cmx-cross-modal-fusion-for-rgb-x-semantic#ran","syntology_url":"https://syntology.ai/paper/2203.04838","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.04838"}}}},{"paper":"/paper/glass-segmentation-using-intensity-and","slug":"glass-segmentation-using-intensity-and","title":"Glass Segmentation Using Intensity and Spectral Polarization Cues","date":"2022-01-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/monoscene-monocular-3d-semantic-scene","slug":"monoscene-monocular-3d-semantic-scene","title":"MonoScene: Monocular 3D Semantic Scene Completion","date":"2021-12-01","arxiv_id":"2112.00726","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":2,"official":{"repos":["cv-rits/MonoScene"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/monoscene-monocular-3d-semantic-scene#ran","syntology_url":"https://syntology.ai/paper/2112.00726","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.00726"}}}},{"paper":"/paper/geometry-uncertainty-projection-network-for","slug":"geometry-uncertainty-projection-network-for","title":"Geometry Uncertainty Projection Network for Monocular 3D Object Detection","date":"2021-07-29","arxiv_id":"2107.13774","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":21,"samples_ran":16,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":6,"samples_unverified":5,"pointer_only_for_licence":2,"official":{"repos":["supermhp/gupnet"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":5,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/geometry-uncertainty-projection-network-for#ran","syntology_url":"https://syntology.ai/paper/2107.13774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.13774"}}}},{"paper":"/paper/perception-aware-multi-sensor-fusion-for-3d","slug":"perception-aware-multi-sensor-fusion-for-3d","title":"EPMF: Efficient Perception-aware Multi-sensor Fusion for 3D Semantic Segmentation","date":"2021-06-21","arxiv_id":"2106.15277","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/multi-modal-fusion-transformer-for-end-to-end","slug":"multi-modal-fusion-transformer-for-end-to-end","title":"Multi-Modal Fusion Transformer for End-to-End Autonomous Driving","date":"2021-04-19","arxiv_id":"2104.09224","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":9,"samples_constructed":7,"samples_ran_checked":8,"samples_ran_instrument_failed":1,"samples_unverified":6,"pointer_only_for_licence":0,"official":{"repos":["autonomousvision/transfuser"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/multi-modal-fusion-transformer-for-end-to-end#ran","syntology_url":"https://syntology.ai/paper/2104.09224","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.09224"}}}},{"paper":"/paper/groomed-nms-grouped-mathematically","slug":"groomed-nms-grouped-mathematically","title":"GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection","date":"2021-03-31","arxiv_id":"2103.17202","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":4,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["abhi1kumar/groomed_nms"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/groomed-nms-grouped-mathematically#ran","syntology_url":"https://syntology.ai/paper/2103.17202","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.17202"}}}},{"paper":"/paper/delving-into-localization-errors-for","slug":"delving-into-localization-errors-for","title":"Delving into Localization Errors for Monocular 3D Object Detection","date":"2021-03-30","arxiv_id":"2103.16237","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["xinzhuma/monodle"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/delving-into-localization-errors-for#ran","syntology_url":"https://syntology.ai/paper/2103.16237","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.16237"}}}},{"paper":"/paper/lmscnet-lightweight-multiscale-3d-semantic","slug":"lmscnet-lightweight-multiscale-3d-semantic","title":"LMSCNet: Lightweight Multiscale 3D Semantic Completion","date":"2020-08-24","arxiv_id":"2008.10559","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/issafe-improving-semantic-segmentation-in","slug":"issafe-improving-semantic-segmentation-in","title":"ISSAFE: Improving Semantic Segmentation in Accidents by Fusing Event-based Data","date":"2020-08-20","arxiv_id":"2008.08974","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/autolabeling-3d-objects-with-differentiable","slug":"autolabeling-3d-objects-with-differentiable","title":"Autolabeling 3D Objects with Differentiable Rendering of SDF Shape Priors","date":"2019-11-26","arxiv_id":"1911.11288","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["TRI-ML/sdflabel"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/autolabeling-3d-objects-with-differentiable#ran","syntology_url":"https://syntology.ai/paper/1911.11288","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.11288"}}}},{"paper":"/paper/acnet-attention-based-network-to-exploit","slug":"acnet-attention-based-network-to-exploit","title":"ACNet: Attention Based Network to Exploit Complementary Features for RGBD Semantic Segmentation","date":"2019-05-24","arxiv_id":"1905.10089","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/deep-hough-voting-for-3d-object-detection-in","slug":"deep-hough-voting-for-3d-object-detection-in","title":"Deep Hough Voting for 3D Object Detection in Point Clouds","date":"2019-04-21","arxiv_id":"1904.09664","rows_on_this_dataset":2,"code_links":13,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":2,"samples_unverified":2,"pointer_only_for_licence":10,"official":{"repos":["facebookresearch/votenet"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/deep-hough-voting-for-3d-object-detection-in#ran","syntology_url":"https://syntology.ai/paper/1904.09664","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.09664"}}}},{"paper":"/paper/pointnet-deep-hierarchical-feature-learning","slug":"pointnet-deep-hierarchical-feature-learning","title":"PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space","date":"2017-06-07","arxiv_id":"1706.02413","rows_on_this_dataset":1,"code_links":68,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":67,"samples_ran":36,"samples_constructed":31,"samples_ran_checked":33,"samples_ran_instrument_failed":3,"samples_unverified":31,"pointer_only_for_licence":26,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/pointnet-deep-hierarchical-feature-learning#ran","syntology_url":"https://syntology.ai/paper/1706.02413","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1706.02413"}}}},{"paper":"/paper/pointnet-deep-learning-on-point-sets-for-3d","slug":"pointnet-deep-learning-on-point-sets-for-3d","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","date":"2016-12-02","arxiv_id":"1612.00593","rows_on_this_dataset":1,"code_links":110,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":164,"samples_ran":103,"samples_constructed":45,"samples_ran_checked":74,"samples_ran_instrument_failed":29,"samples_unverified":61,"pointer_only_for_licence":92,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/pointnet-deep-learning-on-point-sets-for-3d#ran","syntology_url":"https://syntology.ai/paper/1612.00593","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1612.00593"}}}},{"paper":"/paper/semantic-scene-completion-from-a-single-depth","slug":"semantic-scene-completion-from-a-single-depth","title":"Semantic Scene Completion from a Single Depth Image","date":"2016-11-28","arxiv_id":"1611.08974","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["shurans/sscnet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/semantic-scene-completion-from-a-single-depth#ran","syntology_url":"https://syntology.ai/paper/1611.08974","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.08974"}}}}],"papers_where_code_ran":20,"papers_where_code_ran_first_page":"/dataset/kitti-360/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/kitti-360/papers/ran/1","json":"/dataset/kitti-360/papers/ran/1.json","rows":20}],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":21,"samples_harvested":354,"samples_ran":234,"samples_constructed":86,"samples_ran_checked":167,"samples_ran_instrument_failed":67,"samples_unverified":120,"pointer_only_for_licence":148,"papers_with_no_sample_that_ran":1,"papers_with_a_sample_that_ran":20,"papers_with_a_run_with_no_instrument_failure":16,"papers_where_every_run_was_an_instrument_failure":4,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":1,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/3d-semantic-scene-completion-from-a-single-2","since_archive":"/sota/3d-semantic-scene-completion-from-a-single-2#since-judged","papers_judged":1,"placed":0}]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"0e223d2f7d6e1429117844a363ea68c2359abea1d0fdfad2eeb288f9bfc2f4a9","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}