Papers › Spherical Transformer for LiDAR-based 3D Recognition

Spherical Transformer for LiDAR-based 3D Recognition

22 Mar 2023CVPR 2023 1arXiv:2303.12766archive 2025-07-28

Xin Lai, Yukang Chen, Fanbin Lu, Jianhui Liu, Jiaya Jia

LiDAR-based 3D point cloud recognition has benefited various applications. Without specially considering the LiDAR point distribution, most current methods suffer from information disconnection and limited receptive field, especially for the sparse distant points. In this work, we study the varying-sparsity distribution of LiDAR points and present SphereFormer to directly aggregate information from dense close points to the sparse distant ones. We design radial window self-attention that partitions the space into multiple non-overlapping narrow and long windows. It overcomes the disconnection issue and enlarges the receptive field smoothly and dramatically, which significantly boosts the performance of sparse distant points. Moreover, to fit the narrow and long windows, we propose exponential splitting to yield fine-grained position encoding and dynamic feature selection to increase model representation ability. Notably, our method ranks 1st on both nuScenes and SemanticKITTI semantic segmentation benchmarks with 81.9% and 74.8% mIoU, respectively. Also, we achieve the 3rd place on nuScenes object detection benchmark with 72.8% NDS and 68.5% mAP. Code is available at https://github.com/dvlab-research/SphereFormer.git.

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="2303.12766")

Code

Syntology Ran 4 of 13 code samples harvested from 1 repository linked to this paper; 9 have no recorded run. Of those that ran: 4 ran with no contract checked.

By repository: official repository: 13 samples from 1 repository, 4 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/sphereformer officialmentioned in papermentioned on GitHubpytorchApache-2.0 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

13 samples harvested; 4 ran; 0 honoured the contract we drafted; 9 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.

4ran
9unverified

Licence: 0 of the 13 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/sphereformer. “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/sphereformer/util/common_util.py official repository ran Apache-2.0 (permissive) · 1dad93b61e98c32e · report
get_logger dvlab-research/sphereformer/util/logger.py official repository ran Apache-2.0 (permissive) · e985f384ed063aef · report
initialize_scheduler dvlab-research/sphereformer/util/lr.py official repository ran Apache-2.0 (permissive) · 1cfda515a69f8682 · report
intersectionAndUnion dvlab-research/sphereformer/util/common_util.py official repository ran Apache-2.0 (permissive) · 2a66f4ab6863908c · report
cart2sphere dvlab-research/sphereformer/model/spherical_transformer.py official repository unverified Apache-2.0 (permissive) · 0ded69a3ab085049 · report
collate_fn_limit dvlab-research/sphereformer/util/data_util.py official repository unverified Apache-2.0 (permissive) · a7c2ca770f470c6c · report
collation_fn_voxelmean dvlab-research/sphereformer/util/data_util.py official repository unverified Apache-2.0 (permissive) · f9f9d2518f7c1cb8 · report
collation_fn_voxelmean_tta dvlab-research/sphereformer/util/data_util.py official repository unverified Apache-2.0 (permissive) · b2c35d25a8ad278c · report
elastic dvlab-research/sphereformer/util/semantic_kitti.py official repository unverified Apache-2.0 (permissive) · 921e8ddc91e0d8a6 · report
exponential_split dvlab-research/sphereformer/model/spherical_transformer.py official repository unverified Apache-2.0 (permissive) · 3ca452aff97da9d5 · report
intersectionAndUnionGPU dvlab-research/sphereformer/util/common_util.py official repository unverified Apache-2.0 (permissive) · 136834d66336e6b9 · report
load_cfg_from_cfg_file dvlab-research/sphereformer/util/config.py official repository unverified Apache-2.0 (permissive) · 277a13798d6d6981 · report
merge_cfg_from_list dvlab-research/sphereformer/util/config.py official repository unverified Apache-2.0 (permissive) · 4efe685c6fb1ec11 · report

Tasks

3D Object Detection3D Semantic SegmentationLIDAR Semantic SegmentationObject DetectionSemantic Segmentationfeature selectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Semantic Segmentation SemanticKITTI SphereFormer test mIoU 74.8% #4 of 45 Archive leaderboard report
3D Semantic Segmentation SemanticKITTI SphereFormer val mIoU 67.8% #4 of 45 Archive leaderboard report
3D Semantic Segmentation WildScenes SphereFormer mIoU 33.97 #4 of 4 Archive leaderboard report
LIDAR Semantic Segmentation S.MID SphereFormer val mIoU 67.8% #3 of 4 Archive leaderboard report
LIDAR Semantic Segmentation nuScenes SphereFormer test mIoU 0.819 #5 of 36 Archive leaderboard report
LIDAR Semantic Segmentation nuScenes SphereFormer val mIoU 0.795 #5 of 36 Archive leaderboard report
Semantic Segmentation KITTI Semantic Segmentation RPVNet [xu2021rpvnet] Mean IoU (class) 80.7 #1 of 7 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

Feature Selection

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