Papers › Stratified Transformer for 3D Point Cloud Segmentation

Stratified Transformer for 3D Point Cloud Segmentation

28 Mar 2022CVPR 2022 1arXiv:2203.14508archive 2025-07-28

Xin Lai, Jianhui Liu, Li Jiang, LiWei Wang, Hengshuang Zhao, Shu Liu, Xiaojuan Qi, Jiaya Jia

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.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2203.14508")

Code

Syntology Ran 5 of 12 code samples harvested from 1 repository linked to this paper; 7 have no recorded run. Of those that ran: 1 ran · fixture could not drive it; 4 ran with no contract checked.

By repository: official repository: 12 samples from 1 repository, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

dvlab-research/stratified-transformer officialmentioned in papermentioned on GitHubpytorchMIT report
dvlab-research/deepvision3d mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

12 samples harvested; 5 ran; 0 honoured the contract we drafted; 7 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · fixture could not drive it
4ran
7unverified

Licence: 0 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from dvlab-research/stratified-transformer. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

colorize dvlab-research/stratified-transformer/util/common_util.py official repository ran MIT (permissive) · 1dad93b61e98c32e · report
get_indice_pairs dvlab-research/stratified-transformer/model/stratified_transformer.py official repository ran · fixture could not drive it MIT (permissive) · 92a89e85291de713 · report
get_logger dvlab-research/stratified-transformer/util/logger.py official repository ran MIT (permissive) · e985f384ed063aef · report
initialize_scheduler dvlab-research/stratified-transformer/util/lr.py official repository ran MIT (permissive) · 1cfda515a69f8682 · report
intersectionAndUnion dvlab-research/stratified-transformer/util/common_util.py official repository ran MIT (permissive) · 2a66f4ab6863908c · report
collate_fn_limit dvlab-research/stratified-transformer/util/data_util.py official repository unverified MIT (permissive) · f37c5536599dc365 · report
collate_fn_limit_mix3d dvlab-research/stratified-transformer/util/data_util.py official repository unverified MIT (permissive) · 409b9551202d48f6 · report
grid_sample dvlab-research/stratified-transformer/model/stratified_transformer.py official repository unverified MIT (permissive) · 9905bbf6a1511afe · report
intersectionAndUnionGPU dvlab-research/stratified-transformer/util/common_util.py official repository unverified MIT (permissive) · 136834d66336e6b9 · report
load_cfg_from_cfg_file dvlab-research/stratified-transformer/util/config.py official repository unverified MIT (permissive) · 277a13798d6d6981 · report
make_dataset dvlab-research/stratified-transformer/util/dataset.py official repository unverified MIT (permissive) · 3f438ed83e10fc4e · report
merge_cfg_from_list dvlab-research/stratified-transformer/util/config.py official repository unverified MIT (permissive) · 4efe685c6fb1ec11 · report

Tasks

Point Cloud SegmentationSemantic Segmentation

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semantic Segmentation S3DIS Area5 StratifiedTransformer Number of params 8.0M #24 of 61 Archive leaderboard report
Semantic Segmentation S3DIS Area5 StratifiedTransformer mAcc 78.1 #24 of 61 Archive leaderboard report
Semantic Segmentation S3DIS Area5 StratifiedTransformer mIoU 72.0 #24 of 61 Archive leaderboard report
Semantic Segmentation S3DIS Area5 StratifiedTransformer oAcc 91.5 #24 of 61 Archive leaderboard report
Semantic Segmentation ScanNet StratifiedFormer test mIoU 73.7 #23 of 45 Archive leaderboard report
Semantic Segmentation ScanNet StratifiedFormer val mIoU 74.3 #23 of 45 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections