{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/squeezeseg-convolutional-neural-nets-with","title":"SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud","arxiv_id":"1710.07368","date":"2017-10-19","proceeding":null,"authors":["Bichen Wu","Alvin Wan","Xiangyu Yue","Kurt Keutzer"],"abstract":"In this paper, we address semantic segmentation of road-objects from 3D LiDAR\npoint clouds. In particular, we wish to detect and categorize instances of\ninterest, such as cars, pedestrians and cyclists. We formulate this problem as\na point- wise classification problem, and propose an end-to-end pipeline called\nSqueezeSeg based on convolutional neural networks (CNN): the CNN takes a\ntransformed LiDAR point cloud as input and directly outputs a point-wise label\nmap, which is then refined by a conditional random field (CRF) implemented as a\nrecurrent layer. Instance-level labels are then obtained by conventional\nclustering algorithms. Our CNN model is trained on LiDAR point clouds from the\nKITTI dataset, and our point-wise segmentation labels are derived from 3D\nbounding boxes from KITTI. To obtain extra training data, we built a LiDAR\nsimulator into Grand Theft Auto V (GTA-V), a popular video game, to synthesize\nlarge amounts of realistic training data. Our experiments show that SqueezeSeg\nachieves high accuracy with astonishingly fast and stable runtime (8.7 ms per\nframe), highly desirable for autonomous driving applications. Furthermore,\nadditionally training on synthesized data boosts validation accuracy on\nreal-world data. Our source code and synthesized data will be open-sourced.","url_abs":"http://arxiv.org/abs/1710.07368v1","url_pdf":"http://arxiv.org/pdf/1710.07368v1.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":"squeezeseg-convolutional-neural-nets-with","repo_url":"https://github.com/BichenWuUCB/SqueezeSeg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"BSD-2-Clause"}},{"paper_slug":"squeezeseg-convolutional-neural-nets-with","repo_url":"https://github.com/YaraAlnaggar/SqueezeSeg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"BSD-2-Clause"}},{"paper_slug":"squeezeseg-convolutional-neural-nets-with","repo_url":"https://github.com/dablack2020/Seniordes","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"BSD-2-Clause"}},{"paper_slug":"squeezeseg-convolutional-neural-nets-with","repo_url":"https://github.com/xuanyuzhou98/SqueezeSeg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"BSD-2-Clause"}},{"paper_slug":"squeezeseg-convolutional-neural-nets-with","repo_url":"https://github.com/xuanyuzhou98/SqueezeSegV2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"BSD-2-Clause"}}],"tasks":[{"task_slug":"3d-semantic-segmentation","task_name":"3D Semantic Segmentation"},{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"robust-3d-semantic-segmentation","task_name":"Robust 3D Semantic Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-semantic-segmentation-on-semantickitti","task":"3D Semantic Segmentation","dataset":"SemanticKITTI","model":"SqueezeSeg","rank_in_archive_order":37,"of":45,"metrics":{"test mIoU":"29.5%"},"uses_additional_data":false},{"leaderboard":"/sota/robust-3d-semantic-segmentation-on","task":"Robust 3D Semantic Segmentation","dataset":"SemanticKITTI-C","model":"SqueezeSeg (64x2048)","rank_in_archive_order":22,"of":22,"metrics":{"mean Corruption Error (mCE)":"164.87%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1710.07368","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.07368"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/YaraAlnaggar/SqueezeSeg","reach":{"status":"ok","spdx":"BSD-2-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xuanyuzhou98/SqueezeSegV2","reach":{"status":"ok","spdx":"BSD-2-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dablack2020/Seniordes","reach":{"status":"ok","spdx":"BSD-2-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xuanyuzhou98/SqueezeSeg","reach":{"status":"ok","spdx":"BSD-2-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/BichenWuUCB/SqueezeSeg","reach":{"status":"ok","spdx":"BSD-2-Clause"}}],"summary":{"unverified":7},"by_repo_kind":{"listed":{"samples":7,"ran":0,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"6046373ef3efd979","entry":"base_model_config","repo":"BichenWuUCB/SqueezeSeg","repo_kind":"listed","path":"src/config/config.py","file_url":"https://github.com/BichenWuUCB/SqueezeSeg/blob/HEAD/src/config/config.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"6046373ef3efd979"}},{"code_sha256_prefix":"39ffc1ab87f2c16b","entry":"bgr_to_rgb","repo":"BichenWuUCB/SqueezeSeg","repo_kind":"listed","path":"src/utils/util.py","file_url":"https://github.com/BichenWuUCB/SqueezeSeg/blob/HEAD/src/utils/util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"39ffc1ab87f2c16b"}},{"code_sha256_prefix":"d98674c6c141b363","entry":"conf_error_rate_at_thresh_fn","repo":"BichenWuUCB/SqueezeSeg","repo_kind":"listed","path":"src/utils/util.py","file_url":"https://github.com/BichenWuUCB/SqueezeSeg/blob/HEAD/src/utils/util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"d98674c6c141b363"}},{"code_sha256_prefix":"1165011b2e8683ac","entry":"hv_in_range","repo":"YaraAlnaggar/SqueezeSeg","repo_kind":"listed","path":"deliverables/project_to_spherical.py","file_url":"https://github.com/YaraAlnaggar/SqueezeSeg/blob/HEAD/deliverables/project_to_spherical.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"1165011b2e8683ac"}},{"code_sha256_prefix":"0c1695047a189d21","entry":"pto_depth_map","repo":"YaraAlnaggar/SqueezeSeg","repo_kind":"listed","path":"deliverables/project_to_spherical.py","file_url":"https://github.com/YaraAlnaggar/SqueezeSeg/blob/HEAD/deliverables/project_to_spherical.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"0c1695047a189d21"}},{"code_sha256_prefix":"d4ef4918c84b5597","entry":"spherical_project","repo":"YaraAlnaggar/SqueezeSeg","repo_kind":"listed","path":"deliverables/project_to_spherical.py","file_url":"https://github.com/YaraAlnaggar/SqueezeSeg/blob/HEAD/deliverables/project_to_spherical.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"d4ef4918c84b5597"}},{"code_sha256_prefix":"9af1c222357f80b5","entry":"visualize_seg","repo":"BichenWuUCB/SqueezeSeg","repo_kind":"listed","path":"src/utils/util.py","file_url":"https://github.com/BichenWuUCB/SqueezeSeg/blob/HEAD/src/utils/util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"9af1c222357f80b5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}