Papers › Superpoint Transformer for 3D Scene Instance Segmentation

Superpoint Transformer for 3D Scene Instance Segmentation

28 Nov 2022arXiv:2211.15766archive 2025-07-28

Jiahao Sun, Chunmei Qing, Junpeng Tan, Xiangmin Xu

Most existing methods realize 3D instance segmentation by extending those models used for 3D object detection or 3D semantic segmentation. However, these non-straightforward methods suffer from two drawbacks: 1) Imprecise bounding boxes or unsatisfactory semantic predictions limit the performance of the overall 3D instance segmentation framework. 2) Existing method requires a time-consuming intermediate step of aggregation. To address these issues, this paper proposes a novel end-to-end 3D instance segmentation method based on Superpoint Transformer, named as SPFormer. It groups potential features from point clouds into superpoints, and directly predicts instances through query vectors without relying on the results of object detection or semantic segmentation. The key step in this framework is a novel query decoder with transformers that can capture the instance information through the superpoint cross-attention mechanism and generate the superpoint masks of the instances. Through bipartite matching based on superpoint masks, SPFormer can implement the network training without the intermediate aggregation step, which accelerates the network. Extensive experiments on ScanNetv2 and S3DIS benchmarks verify that our method is concise yet efficient. Notably, SPFormer exceeds compared state-of-the-art methods by 4.3% on ScanNetv2 hidden test set in terms of mAP and keeps fast inference speed (247ms per frame) simultaneously. Code is available at https://github.com/sunjiahao1999/SPFormer.

Paper PDF Code

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

Code

sunjiahao1999/spformer officialmentioned in papermentioned on GitHubpytorchMIT 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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D Instance Segmentation 3D Object Detection 3D Semantic Segmentation Decoder Instance Segmentation Object Detection Segmentation Semantic Segmentation object-detection

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
3D Instance Segmentation	S3DIS	SPFormer	AP@50	69.2	#8 of 21	Archive leaderboard	report
3D Instance Segmentation	S3DIS	SPFormer	mPrec	74.0	#8 of 21	Archive leaderboard	report
3D Instance Segmentation	S3DIS	SPFormer	mRec	71.1	#8 of 21	Archive leaderboard	report
3D Instance Segmentation	ScanNet(v2)	SPFormer	mAP	54.9	#8 of 32	Archive leaderboard	report
3D Instance Segmentation	ScanNet(v2)	SPFormer	mAP @ 50	77.0	#8 of 32	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

Adam Attention BPE Dense Connections Dropout Label Smoothing Layer Normalization Linear Layer Multi-Head Attention Position-Wise Feed-Forward Layer Residual Connection SPEED Softmax Test Transformer

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