mlsanityData to 14 Oct 2026

MarS3D: A Plug-and-Play Motion-Aware Model for Semantic Segmentation on Multi-Scan 3D Point Clouds

arXiv 2307.09316 ↗First posted 18 Jul 2023cs.CVcited by 19

Not on the map. Why?

Abstract (arXiv)

3D semantic segmentation on multi-scan large-scale point clouds plays an important role in autonomous systems. Unlike the single-scan-based semantic segmentation task, this task requires distinguishing the motion states of points in addition to their semantic categories. However, methods designed for single-scan-based segmentation tasks perform poorly on the multi-scan task due to the lacking of an effective way to integrate temporal information. We propose MarS3D, a plug-and-play motion-aware module for semantic segmentation on multi-scan 3D point clouds. This module can be flexibly combined with single-scan models to allow them to have multi-scan perception abilities. The model encompasses two key designs: the Cross-Frame Feature Embedding module for enriching representation learning and the Motion-Aware Feature Learning module for enhancing motion awareness. Extensive experiments show that MarS3D can improve the performance of the baseline model by a large margin. The code is available at https://github.com/CVMI-Lab/MarS3D.

Key facts. Cited by 19 papers in the map (data through 14 Oct 2026). Builds on 35 of its 41 references that are in the map. First posted on arXiv 18 Jul 2023.

Builds on

35 of 41 references.

References · 35

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  4. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  5. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  6. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  7. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,715
  8. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  9. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,208
  10. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  11. 2022BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representationcited by 850
  12. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 748
23 more
  1. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 657
  2. 2019Video Object Segmentation using Space-Time Memory Networkscited by 438
  3. 2020Searching Efficient 3D Architectures with Sparse Point-Voxel Convolutioncited by 423
  4. 2020PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentationcited by 275
  5. 2017Submanifold Sparse Convolutional Networkscited by 223
  6. 2020Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completioncited by 223
  7. 2021PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Cloudscited by 211
  8. 2021RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentationcited by 173
  9. 2021(AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Networkcited by 164
  10. 20222DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Cloudscited by 158
  11. 2022Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentationcited by 119
  12. 2020Cylinder3D: An Effective 3D Framework for Driving-scene LiDAR Semantic Segmentationcited by 112
  13. 2020Learning What to Learn for Video Object Segmentationcited by 89
  14. 2020Temporally Distributed Networks for Fast Video Semantic Segmentationcited by 77
  15. 2020Learning Fast and Robust Target Models for Video Object Segmentationcited by 76
  16. 2020Efficient Semantic Video Segmentation with Per-frame Inferencecited by 63
  17. 2020FISHING Net: Future Inference of Semantic Heatmaps In Gridscited by 55
  18. 2020Memory Aggregation Networks for Efficient Interactive Video Object Segmentationcited by 40
  19. 2019Every Frame Counts: Joint Learning of Video Segmentation and Optical Flowcited by 31
  20. 2021LiDAR-based Recurrent 3D Semantic Segmentation with Temporal Memory Alignmentcited by 26
  21. 2022Meta-RangeSeg: LiDAR Sequence Semantic Segmentation Using Multiple Feature Aggregationcited by 23
  22. 2022Abstract Flow for Temporal Semantic Segmentation on the Permutohedral Latticecited by 9
  23. 2021Efficient Urban-scale Point Clouds Segmentation with BEV Projectioncited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 7; 2025: 5; 2026: 4.

19 papers.

Sort:

By area:

  1. 2023UniPAD: A Universal Pre-training Paradigm for Autonomous Drivingcited by 73
  2. 2023Mask-Attention-Free Transformer for 3D Instance Segmentationcited by 46
  3. 2024How Far are AI-generated Videos from Simulating the 3D Visual World: A Learned 3D Evaluation Approachcited by 16
  4. 2023TFNet: Exploiting Temporal Cues for Fast and Accurate LiDAR Semantic Segmentationcited by 13
  5. 2024TASeg: Temporal Aggregation Network for LiDAR Semantic Segmentationcited by 13
  6. 2024Total-Decom: Decomposed 3D Scene Reconstruction with Minimal Interactioncited by 12
  7. 2024Can OOD Object Detectors Learn from Foundation Models?cited by 10
  8. 2025Aligning Effective Tokens with Video Anomaly in Large Language Modelscited by 8
  9. 2024SegNet4D: Efficient Instance-Aware 4D Semantic Segmentation for LiDAR Point Cloudcited by 5
  10. 2025Equipping Vision Foundation Model with Mixture of Experts for Out-of-Distribution Detectioncited by 5
  11. 2024Subspace Prototype Guidance for Mitigating Class Imbalance in Point Cloud Semantic Segmentationcited by 4
  12. 2025HiLoTs: High-Low Temporal Sensitive Representation Learning for Semi-Supervised LiDAR Segmentation in Autonomous Drivingcited by 3
7 more
  1. 2024A Preprocessing and Postprocessing Voxel-based Method for LiDAR Semantic Segmentation Improvement in Long Distancecited by 0
  2. 20254D-CS: Exploiting Cluster Prior for 4D Spatio-Temporal LiDAR Semantic Segmentationcited by 0
  3. 20254DSegStreamer: Streaming 4D Panoptic Segmentation via Dual Threadscited by 0
  4. 2026DriveFix: Spatio-Temporally Coherent Driving Scene Restorationcited by 0
  5. 2026Learning to See through Illumination Extremes with Event Streaming in Multimodal Large Language Modelscited by 0
  6. 2026Dataset Distillation by Influence Matchingcited by 0
  7. 2026Bootstrapping a 4D LiDAR Annotation Tool from Video Foundation Modelscited by 0