{"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/vote3deep-fast-object-detection-in-3d-point","title":"Vote3Deep: Fast Object Detection in 3D Point Clouds Using Efficient Convolutional Neural Networks","arxiv_id":"1609.06666","date":"2016-09-21","proceeding":null,"authors":["Martin Engelcke","Dushyant Rao","Dominic Zeng Wang","Chi Hay Tong","Ingmar Posner"],"abstract":"This paper proposes a computationally efficient approach to detecting objects\nnatively in 3D point clouds using convolutional neural networks (CNNs). In\nparticular, this is achieved by leveraging a feature-centric voting scheme to\nimplement novel convolutional layers which explicitly exploit the sparsity\nencountered in the input. To this end, we examine the trade-off between\naccuracy and speed for different architectures and additionally propose to use\nan L1 penalty on the filter activations to further encourage sparsity in the\nintermediate representations. To the best of our knowledge, this is the first\nwork to propose sparse convolutional layers and L1 regularisation for efficient\nlarge-scale processing of 3D data. We demonstrate the efficacy of our approach\non the KITTI object detection benchmark and show that Vote3Deep models with as\nfew as three layers outperform the previous state of the art in both laser and\nlaser-vision based approaches by margins of up to 40% while remaining highly\ncompetitive in terms of processing time.","url_abs":"http://arxiv.org/abs/1609.06666v2","url_pdf":"http://arxiv.org/pdf/1609.06666v2.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":[],"tasks":[{"task_slug":"3d-object-detection","task_name":"3D Object Detection"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"real-time-object-detection","task_name":"Real-Time Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"feature-centric-voting","method_name":"Feature-Centric Voting"},{"method_slug":"l1-regularization","method_name":"L1 Regularization"},{"method_slug":"non-maximum-suppression","method_name":"Non Maximum Suppression"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"speed","method_name":"SPEED"},{"method_slug":"sparse-convolutions","method_name":"Sparse Convolutions"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/object-detection-on-kitti-cars-easy","task":"Object Detection","dataset":"KITTI Cars Easy","model":"Vote3Deep","rank_in_archive_order":4,"of":5,"metrics":{"AP":"76.79"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-kitti-cars-hard","task":"Object Detection","dataset":"KITTI Cars Hard","model":"Vote3Deep","rank_in_archive_order":3,"of":5,"metrics":{"AP":"63.23"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-kitti-cars-moderate","task":"Object Detection","dataset":"KITTI Cars Moderate","model":"Vote3Deep","rank_in_archive_order":3,"of":4,"metrics":{"AP":"68.24"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-kitti-cyclists-easy","task":"Object Detection","dataset":"KITTI Cyclists Easy","model":"Vote3Deep","rank_in_archive_order":1,"of":1,"metrics":{"AP":"79.92"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-kitti-cyclists-hard","task":"Object Detection","dataset":"KITTI Cyclists Hard","model":"Vote3Deep","rank_in_archive_order":1,"of":1,"metrics":{"AP":"62.98"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-kitti-cyclists-moderate","task":"Object Detection","dataset":"KITTI Cyclists Moderate","model":"Vote3Deep","rank_in_archive_order":1,"of":1,"metrics":{"AP":"67.88"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-kitti-pedestrians-easy","task":"Object Detection","dataset":"KITTI Pedestrians Easy","model":"Vote3Deep","rank_in_archive_order":1,"of":1,"metrics":{"AP":"68.39"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-kitti-pedestrians-hard","task":"Object Detection","dataset":"KITTI Pedestrians Hard","model":"Vote3Deep","rank_in_archive_order":1,"of":1,"metrics":{"AP":"52.59"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-kitti-pedestrians","task":"Object Detection","dataset":"KITTI Pedestrians Moderate","model":"Vote3Deep","rank_in_archive_order":1,"of":1,"metrics":{"AP":"55.37"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1609.06666","atlas_url":"https://app.syntology.ai/?focus=1609.06666","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":"1609.06666"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1609.06666\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1609.06666"},"call":"get_concepts_for_paper(arxiv_id=\"1609.06666\")"}],"by_repo":[],"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":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"65675ef3d7fe1a20678d3ddefd2da6a2c206821a3deda28547cc92a9bf81c055","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}