{"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/squeezesegv3-spatially-adaptive-convolution","title":"SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation","arxiv_id":"2004.01803","date":"2020-04-03","proceeding":"ECCV 2020 8","authors":["Chenfeng Xu","Bichen Wu","Zining Wang","Wei Zhan","Peter Vajda","Kurt Keutzer","Masayoshi Tomizuka"],"abstract":"LiDAR point-cloud segmentation is an important problem for many applications. For large-scale point cloud segmentation, the \\textit{de facto} method is to project a 3D point cloud to get a 2D LiDAR image and use convolutions to process it. Despite the similarity between regular RGB and LiDAR images, we discover that the feature distribution of LiDAR images changes drastically at different image locations. Using standard convolutions to process such LiDAR images is problematic, as convolution filters pick up local features that are only active in specific regions in the image. As a result, the capacity of the network is under-utilized and the segmentation performance decreases. To fix this, we propose Spatially-Adaptive Convolution (SAC) to adopt different filters for different locations according to the input image. SAC can be computed efficiently since it can be implemented as a series of element-wise multiplications, im2col, and standard convolution. It is a general framework such that several previous methods can be seen as special cases of SAC. Using SAC, we build SqueezeSegV3 for LiDAR point-cloud segmentation and outperform all previous published methods by at least 3.7% mIoU on the SemanticKITTI benchmark with comparable inference speed.","url_abs":"https://arxiv.org/abs/2004.01803v2","url_pdf":"https://arxiv.org/pdf/2004.01803v2.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":"squeezesegv3-spatially-adaptive-convolution","repo_url":"https://github.com/chenfengxu714/SqueezeSegV3","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-2-Clause"}},{"paper_slug":"squeezesegv3-spatially-adaptive-convolution","repo_url":"https://github.com/chenfengxu714/YOGO","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-2-Clause"}},{"paper_slug":"squeezesegv3-spatially-adaptive-convolution","repo_url":"https://github.com/PaddlePaddle/Paddle3D","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"3d-semantic-segmentation","task_name":"3D Semantic Segmentation"},{"task_slug":"point-cloud-segmentation","task_name":"Point Cloud Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-semantic-segmentation-on-semantickitti","task":"3D Semantic Segmentation","dataset":"SemanticKITTI","model":"SqueezeSegV3","rank_in_archive_order":26,"of":45,"metrics":{"test mIoU":"55.9%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2004.01803","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.01803"}},"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/chenfengxu714/SqueezeSegV3","reach":{"status":"ok","spdx":"BSD-2-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/chenfengxu714/YOGO","reach":{"status":"ok","spdx":"BSD-2-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/PaddlePaddle/Paddle3D","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":2},"by_repo_kind":{"official":{"samples":2,"ran":0,"repositories":1}},"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":"6175d817c01a13bc","entry":"convert_model","repo":"chenfengxu714/SqueezeSegV3","repo_kind":"official","path":"src/common/sync_batchnorm/batchnorm.py","file_url":"https://github.com/chenfengxu714/SqueezeSegV3/blob/HEAD/src/common/sync_batchnorm/batchnorm.py","link_basis":"first_harvest_node","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":"6175d817c01a13bc"}},{"code_sha256_prefix":"02c1b4046f696eeb","entry":"patch_replication_callback","repo":"chenfengxu714/SqueezeSegV3","repo_kind":"official","path":"src/common/sync_batchnorm/replicate.py","file_url":"https://github.com/chenfengxu714/SqueezeSegV3/blob/HEAD/src/common/sync_batchnorm/replicate.py","link_basis":"first_harvest_node","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":"02c1b4046f696eeb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}