mlsanityData to 14 Oct 2026

Depth-Aware Range Image-Based Model for Point Cloud Segmentation

arXiv 2503.14955 ↗First posted 19 Mar 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Point cloud segmentation (PCS) aims to separate points into different and meaningful groups. The task plays an important role in robotics because PCS enables robots to understand their physical environments directly. To process sparse and large-scale outdoor point clouds in real time, range image-based models are commonly adopted. However, in a range image, the lack of explicit depth information inevitably causes some separate objects in 3D space to touch each other, bringing difficulty for the range image-based models in correctly segmenting the objects. Moreover, previous PCS models are usually derived from the existing color image-based models and unable to make full use of the implicit but ordered depth information inherent in the range image, thereby achieving inferior performance. In this paper, we propose Depth-Aware Module (DAM) and Fast FMVNet V3. DAM perceives the ordered depth information in the range image by explicitly modelling the interdependence among channels. Fast FMVNet V3 incorporates DAM by integrating it into the last block in each architecture stage. Extensive experiments conducted on SemanticKITTI, nuScenes, and SemanticPOSS demonstrate that DAM brings a significant improvement for Fast FMVNet V3 with negligible computational cost.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 44 of its 47 references that are in the map. First posted on arXiv 19 Mar 2025.

Builds on

44 of 47 references.

References · 44

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  5. 2017Squeeze-and-Excitation Networkscited by 4,789
  6. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  7. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  8. 2022A ConvNet for the 2020scited by 3,579
  9. 2018YOLOv3: An Incremental Improvementcited by 2,659
  10. 2018CBAM: Convolutional Block Attention Modulecited by 2,477
  11. 2022BLOOM: A 176B-Parameter Open-Access Multilingual Language Modelcited by 1,984
  12. 2018Unified Perceptual Parsing for Scene Understandingcited by 1,271
32 more
  1. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,208
  2. 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,060
  3. 2021Going deeper with Image Transformerscited by 764
  4. 2023ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoderscited by 712
  5. 2023Point Transformer V3: Simpler, Faster, Strongercited by 589
  6. 2017Convolutional Sequence to Sequence Learningcited by 552
  7. 2021MetaFormer Is Actually What You Need for Visioncited by 524
  8. 2020Searching Efficient 3D Architectures with Sparse Point-Voxel Convolutioncited by 423
  9. 2020Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentationcited by 389
  10. 2023The Impact of Positional Encoding on Length Generalization in Transformerscited by 327
  11. 2022SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentationcited by 252
  12. 2017SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloudcited by 232
  13. 2018SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloudcited by 228
  14. 2022Focal Modulation Networkscited by 186
  15. 2020SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentationcited by 170
  16. 2021Panoptic nuScenes: A Large-Scale Benchmark for LiDAR Panoptic Segmentation and Trackingcited by 166
  17. 2021RangeDet:In Defense of Range View for LiDAR-based 3D Object Detectioncited by 140
  18. 2023Rethinking Range View Representation for LiDAR Segmentationcited by 128
  19. 2020SemanticPOSS: A Point Cloud Dataset with Large Quantity of Dynamic Instancescited by 123
  20. 2021SuMa++: Efficient LiDAR-based Semantic SLAMcited by 100
  21. 2022LaserMix for Semi-Supervised LiDAR Semantic Segmentationcited by 93
  22. 2023RangeViT: Towards Vision Transformers for 3D Semantic Segmentation in Autonomous Drivingcited by 76
  23. 2022PolarMix: A General Data Augmentation Technique for LiDAR Point Cloudscited by 74
  24. 2023UniSeg: A Unified Multi-Modal LiDAR Segmentation Network and the OpenPCSeg Codebasecited by 57
  25. 2022CENet: Toward Concise and Efficient LiDAR Semantic Segmentation for Autonomous Drivingcited by 56
  26. 2023Using a Waffle Iron for Automotive Point Cloud Semantic Segmentationcited by 53
  27. 2021FIDNet: LiDAR Point Cloud Semantic Segmentation with Fully Interpolation Decodingcited by 46
  28. 2020Multi-scale Interaction for Real-time LiDAR Data Segmentation on an Embedded Platformcited by 40
  29. 2021SA-LOAM: Semantic-aided LiDAR SLAM with Loop Closurecited by 14
  30. 2024An Empirical Study of Training State-of-the-Art LiDAR Segmentation Modelscited by 12
  31. 2024Filling Missing Values Matters for Range Image-Based Point Cloud Segmentationcited by 4
  32. 2024Trainable Pointwise Decoder Module for Point Cloud Segmentationcited by 2

Built on by

Not cited yet.