{"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/stratified-transformer-for-3d-point-cloud","title":"Stratified Transformer for 3D Point Cloud Segmentation","arxiv_id":"2203.14508","date":"2022-03-28","proceeding":"CVPR 2022 1","authors":["Xin Lai","Jianhui Liu","Li Jiang","LiWei Wang","Hengshuang Zhao","Shu Liu","Xiaojuan Qi","Jiaya Jia"],"abstract":"3D point cloud segmentation has made tremendous progress in recent years. Most current methods focus on aggregating local features, but fail to directly model long-range dependencies. In this paper, we propose Stratified Transformer that is able to capture long-range contexts and demonstrates strong generalization ability and high performance. Specifically, we first put forward a novel key sampling strategy. For each query point, we sample nearby points densely and distant points sparsely as its keys in a stratified way, which enables the model to enlarge the effective receptive field and enjoy long-range contexts at a low computational cost. Also, to combat the challenges posed by irregular point arrangements, we propose first-layer point embedding to aggregate local information, which facilitates convergence and boosts performance. Besides, we adopt contextual relative position encoding to adaptively capture position information. Finally, a memory-efficient implementation is introduced to overcome the issue of varying point numbers in each window. Extensive experiments demonstrate the effectiveness and superiority of our method on S3DIS, ScanNetv2 and ShapeNetPart datasets. Code is available at https://github.com/dvlab-research/Stratified-Transformer.","url_abs":"https://arxiv.org/abs/2203.14508v1","url_pdf":"https://arxiv.org/pdf/2203.14508v1.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":"stratified-transformer-for-3d-point-cloud","repo_url":"https://github.com/dvlab-research/stratified-transformer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"stratified-transformer-for-3d-point-cloud","repo_url":"https://github.com/dvlab-research/deepvision3d","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"stratified-transformer-for-3d-point-cloud","repo_url":"https://github.com/Pointcept/Pointcept","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"stratified-transformer-for-3d-point-cloud","repo_url":"https://github.com/gofinge/pointtransformerv2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"point-cloud-segmentation","task_name":"Point Cloud Segmentation"},{"task_slug":null,"task_name":"Position"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semantic-segmentation-on-s3dis-area5","task":"Semantic Segmentation","dataset":"S3DIS Area5","model":"StratifiedTransformer","rank_in_archive_order":24,"of":61,"metrics":{"Number of params":"8.0M","mAcc":"78.1","mIoU":"72.0","oAcc":"91.5"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-scannet","task":"Semantic Segmentation","dataset":"ScanNet","model":"StratifiedFormer","rank_in_archive_order":23,"of":45,"metrics":{"test mIoU":"73.7","val mIoU":"74.3"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2203.14508","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.14508"}},"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/dvlab-research/stratified-transformer","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dvlab-research/deepvision3d","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Pointcept/Pointcept","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gofinge/pointtransformerv2","reach":{"status":"ok"}}],"summary":{"ran":4,"ran_fixture":1,"unverified":7},"by_repo_kind":{"official":{"samples":12,"ran":5,"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":"1dad93b61e98c32e","entry":"colorize","repo":"dvlab-research/stratified-transformer","repo_kind":"official","path":"util/common_util.py","file_url":"https://github.com/dvlab-research/stratified-transformer/blob/HEAD/util/common_util.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1dad93b61e98c32e"}},{"code_sha256_prefix":"92a89e85291de713","entry":"get_indice_pairs","repo":"dvlab-research/stratified-transformer","repo_kind":"official","path":"model/stratified_transformer.py","file_url":"https://github.com/dvlab-research/stratified-transformer/blob/HEAD/model/stratified_transformer.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"92a89e85291de713"}},{"code_sha256_prefix":"e985f384ed063aef","entry":"get_logger","repo":"dvlab-research/stratified-transformer","repo_kind":"official","path":"util/logger.py","file_url":"https://github.com/dvlab-research/stratified-transformer/blob/HEAD/util/logger.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e985f384ed063aef"}},{"code_sha256_prefix":"1cfda515a69f8682","entry":"initialize_scheduler","repo":"dvlab-research/stratified-transformer","repo_kind":"official","path":"util/lr.py","file_url":"https://github.com/dvlab-research/stratified-transformer/blob/HEAD/util/lr.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1cfda515a69f8682"}},{"code_sha256_prefix":"2a66f4ab6863908c","entry":"intersectionAndUnion","repo":"dvlab-research/stratified-transformer","repo_kind":"official","path":"util/common_util.py","file_url":"https://github.com/dvlab-research/stratified-transformer/blob/HEAD/util/common_util.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2a66f4ab6863908c"}},{"code_sha256_prefix":"f37c5536599dc365","entry":"collate_fn_limit","repo":"dvlab-research/stratified-transformer","repo_kind":"official","path":"util/data_util.py","file_url":"https://github.com/dvlab-research/stratified-transformer/blob/HEAD/util/data_util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f37c5536599dc365"}},{"code_sha256_prefix":"409b9551202d48f6","entry":"collate_fn_limit_mix3d","repo":"dvlab-research/stratified-transformer","repo_kind":"official","path":"util/data_util.py","file_url":"https://github.com/dvlab-research/stratified-transformer/blob/HEAD/util/data_util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"409b9551202d48f6"}},{"code_sha256_prefix":"9905bbf6a1511afe","entry":"grid_sample","repo":"dvlab-research/stratified-transformer","repo_kind":"official","path":"model/stratified_transformer.py","file_url":"https://github.com/dvlab-research/stratified-transformer/blob/HEAD/model/stratified_transformer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9905bbf6a1511afe"}},{"code_sha256_prefix":"136834d66336e6b9","entry":"intersectionAndUnionGPU","repo":"dvlab-research/stratified-transformer","repo_kind":"official","path":"util/common_util.py","file_url":"https://github.com/dvlab-research/stratified-transformer/blob/HEAD/util/common_util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"136834d66336e6b9"}},{"code_sha256_prefix":"277a13798d6d6981","entry":"load_cfg_from_cfg_file","repo":"dvlab-research/stratified-transformer","repo_kind":"official","path":"util/config.py","file_url":"https://github.com/dvlab-research/stratified-transformer/blob/HEAD/util/config.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"277a13798d6d6981"}},{"code_sha256_prefix":"3f438ed83e10fc4e","entry":"make_dataset","repo":"dvlab-research/stratified-transformer","repo_kind":"official","path":"util/dataset.py","file_url":"https://github.com/dvlab-research/stratified-transformer/blob/HEAD/util/dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3f438ed83e10fc4e"}},{"code_sha256_prefix":"4efe685c6fb1ec11","entry":"merge_cfg_from_list","repo":"dvlab-research/stratified-transformer","repo_kind":"official","path":"util/config.py","file_url":"https://github.com/dvlab-research/stratified-transformer/blob/HEAD/util/config.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4efe685c6fb1ec11"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}