mlsanityData to 7 Oct 2026

MSTA3D: Multi-scale Twin-attention for 3D Instance Segmentation

arXiv 2411.01781 ↗First posted 4 Nov 2024cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Recently, transformer-based techniques incorporating superpoints have become prevalent in 3D instance segmentation. However, they often encounter an over-segmentation problem, especially noticeable with large objects. Additionally, unreliable mask predictions stemming from superpoint mask prediction further compound this issue. To address these challenges, we propose a novel framework called MSTA3D. It leverages multi-scale feature representation and introduces a twin-attention mechanism to effectively capture them. Furthermore, MSTA3D integrates a box query with a box regularizer, offering a complementary spatial constraint alongside semantic queries. Experimental evaluations on ScanNetV2, ScanNet200 and S3DIS datasets demonstrate that our approach surpasses state-of-the-art 3D instance segmentation methods.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 36 of its 46 references that are in the map. First posted on arXiv 4 Nov 2024.

Builds on

36 of 46 references.

References · 36

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2016Layer Normalizationcited by 5,579
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  5. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  6. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,284
  7. 2018Dual Attention Network for Scene Segmentationcited by 1,001
  8. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
  9. 2022DN-DETR: Accelerate DETR Training by Introducing Query DeNoisingcited by 486
  10. 2017Joint 2D-3D-Semantic Data for Indoor Scene Understandingcited by 404
  11. 2017Large-scale Point Cloud Semantic Segmentation with Superpoint Graphscited by 384
  12. 2019A Survey of Autonomous Driving: Common Practices and Emerging Technologiescited by 373
24 more
  1. 2020PointGroup: Dual-Set Point Grouping for 3D Instance Segmentationcited by 318
  2. 2022Mask3D: Mask Transformer for 3D Semantic Instance Segmentationcited by 299
  3. 20183D-SIS: 3D Semantic Instance Segmentation of RGB-D Scanscited by 216
  4. 2022SoftGroup for 3D Instance Segmentation on Point Cloudscited by 197
  5. 2020OccuSeg: Occupancy-aware 3D Instance Segmentationcited by 177
  6. 20203D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentationcited by 140
  7. 2021Hierarchical Aggregation for 3D Instance Segmentationcited by 126
  8. 2022Superpoint Transformer for 3D Scene Instance Segmentationcited by 115
  9. 2016Dual Attention Networks for Multimodal Reasoning and Matchingcited by 113
  10. 2021Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networkscited by 98
  11. 2020Unseen Object Instance Segmentation for Robotic Environmentscited by 85
  12. 20193D Instance Segmentation via Multi-Task Metric Learningcited by 79
  13. 2020DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolutioncited by 74
  14. 2019JSIS3D: Joint Semantic-Instance Segmentation of 3D Point Clouds with Multi-Task Pointwise Networks and Multi-Value Conditional Random Fieldscited by 62
  15. 2023ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolutioncited by 52
  16. 2018Dual Attention Matching Network for Context-Aware Feature Sequence based Person Re-Identificationcited by 50
  17. 2023Mask-Attention-Free Transformer for 3D Instance Segmentationcited by 45
  18. 2020Learning Gaussian Instance Segmentation in Point Cloudscited by 33
  19. 2022MaskGroup: Hierarchical Point Grouping and Masking for 3D Instance Segmentationcited by 29
  20. 2022Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise Binarizationcited by 26
  21. 2022PointInst3D: Segmenting 3D Instances by Pointscited by 16
  22. 2022Scalable SoftGroup for 3D Instance Segmentation on Point Cloudscited by 14
  23. 2022NeuralBF: Neural Bilateral Filtering for Top-down Instance Segmentation on Point Cloudscited by 12
  24. 2023Dual Path Transformer with Partition Attentioncited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 2.

4 papers.

  1. 2025Sketchy Bounding-box Supervision for 3D Instance Segmentationcited by 4
  2. 2026LaSSM: Efficient Semantic-Spatial Query Decoding via Local Aggregation and State Space Models for 3D Instance Segmentationcited by 3
  3. 2024AURORA: Automated Unleash of 3D Room Outlines for VR Applicationscited by 0
  4. 2026Learning from Multimodal Pseudo-Labels for Robust Open-Vocabulary Instance and Panoptic Segmentationcited by 0