{"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":"/paper/multi-modality-cut-and-paste-for-3d-object","title":"Exploring Data Augmentation for Multi-Modality 3D Object Detection","arxiv_id":"2012.12741","date":"2020-12-23","proceeding":null,"authors":["Wenwei Zhang","Zhe Wang","Chen Change Loy"],"abstract":"It is counter-intuitive that multi-modality methods based on point cloud and images perform only marginally better or sometimes worse than approaches that solely use point cloud. This paper investigates the reason behind this phenomenon. Due to the fact that multi-modality data augmentation must maintain consistency between point cloud and images, recent methods in this field typically use relatively insufficient data augmentation. This shortage makes their performance under expectation. Therefore, we contribute a pipeline, named transformation flow, to bridge the gap between single and multi-modality data augmentation with transformation reversing and replaying. In addition, considering occlusions, a point in different modalities may be occupied by different objects, making augmentations such as cut and paste non-trivial for multi-modality detection. We further present Multi-mOdality Cut and pAste (MoCa), which simultaneously considers occlusion and physical plausibility to maintain the multi-modality consistency. Without using ensemble of detectors, our multi-modality detector achieves new state-of-the-art performance on nuScenes dataset and competitive performance on KITTI 3D benchmark. Our method also wins the best PKL award in the 3rd nuScenes detection challenge. Code and models will be released at https://github.com/open-mmlab/mmdetection3d.","url_abs":"https://arxiv.org/abs/2012.12741v2","url_pdf":"https://arxiv.org/pdf/2012.12741v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"multi-modality-cut-and-paste-for-3d-object","repo_url":"https://github.com/open-mmlab/mmdetection3d","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"multi-modality-cut-and-paste-for-3d-object","repo_url":"https://github.com/AllenPeng0209/deeproute_competition","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"multi-modality-cut-and-paste-for-3d-object","repo_url":"https://github.com/Discover304/MMDetection3D-Eloss","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"multi-modality-cut-and-paste-for-3d-object","repo_url":"https://github.com/bosszhe/vimi","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"multi-modality-cut-and-paste-for-3d-object","repo_url":"https://github.com/jhkim-spa/FVNet_v2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"multi-modality-cut-and-paste-for-3d-object","repo_url":"https://github.com/konyul/mmdet3d","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"multi-modality-cut-and-paste-for-3d-object","repo_url":"https://github.com/vision-agh/pointpillars-backbone","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"multi-modality-cut-and-paste-for-3d-object","repo_url":"https://github.com/vision-agh/pointpillars_backbone","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"multi-modality-cut-and-paste-for-3d-object","repo_url":"https://github.com/yhbcode000/MMDetection3D-Eloss","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"3d-object-detection","task_name":"3D Object Detection"},{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2012.12741","atlas_url":"https://app.syntology.ai/?focus=2012.12741","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2012.12741"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2012.12741\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2012.12741"},"call":"get_concepts_for_paper(arxiv_id=\"2012.12741\")"}],"by_repo":[{"repo":"open-mmlab/mmdetection3d","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2405.14870"],"harvested_for_calls":[{"arxiv_id":"2405.14870","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2405.14870"},"call":"get_harvested_code_for_paper(arxiv_id=\"2405.14870\")"}]},{"repo":"AllenPeng0209/deeproute_competition","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2104.10956"],"harvested_for_calls":[{"arxiv_id":"2104.10956","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2104.10956"},"call":"get_harvested_code_for_paper(arxiv_id=\"2104.10956\")"}]},{"repo":"Discover304/MMDetection3D-Eloss","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2104.10956"],"harvested_for_calls":[{"arxiv_id":"2104.10956","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2104.10956"},"call":"get_harvested_code_for_paper(arxiv_id=\"2104.10956\")"}]},{"repo":"bosszhe/vimi","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2303.10975"],"harvested_for_calls":[{"arxiv_id":"2303.10975","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2303.10975"},"call":"get_harvested_code_for_paper(arxiv_id=\"2303.10975\")"}]},{"repo":"jhkim-spa/FVNet_v2","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2104.10956"],"harvested_for_calls":[{"arxiv_id":"2104.10956","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2104.10956"},"call":"get_harvested_code_for_paper(arxiv_id=\"2104.10956\")"}]},{"repo":"konyul/mmdet3d","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2104.10956"],"harvested_for_calls":[{"arxiv_id":"2104.10956","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2104.10956"},"call":"get_harvested_code_for_paper(arxiv_id=\"2104.10956\")"}]},{"repo":"vision-agh/pointpillars-backbone","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"vision-agh/pointpillars_backbone","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"yhbcode000/MMDetection3D-Eloss","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"3241be2fa76f66d65d9a3115f3b26226692fbf9eb82a293732dcb9ff50ebb077","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}