mlsanityData to 7 Oct 2026

Three Cars Approaching within 100m! Enhancing Distant Geometry by Tri-Axis Voxel Scanning for Camera-based Semantic Scene Completion

arXiv 2411.16129 ↗First posted 25 Nov 2024cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Camera-based Semantic Scene Completion (SSC) is gaining attentions in the 3D perception field. However, properties such as perspective and occlusion lead to the underestimation of the geometry in distant regions, posing a critical issue for safety-focused autonomous driving systems. To tackle this, we propose ScanSSC, a novel camera-based SSC model composed of a Scan Module and Scan Loss, both designed to enhance distant scenes by leveraging context from near-viewpoint scenes. The Scan Module uses axis-wise masked attention, where each axis employing a near-to-far cascade masking that enables distant voxels to capture relationships with preceding voxels. In addition, the Scan Loss computes the cross-entropy along each axis between cumulative logits and corresponding class distributions in a near-to-far direction, thereby propagating rich context-aware signals to distant voxels. Leveraging the synergy between these components, ScanSSC achieves state-of-the-art performance, with IoUs of 44.54 and 48.29, and mIoUs of 17.40 and 20.14 on the SemanticKITTI and SSCBench-KITTI-360 benchmarks.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 38 of its 51 references that are in the map. First posted on arXiv 25 Nov 2024.

Builds on

38 of 51 references.

References · 38

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2020End-to-End Object Detection with Transformerscited by 7,384
  4. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  5. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  6. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  7. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,213
  8. 2020Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3Dcited by 1,040
  9. 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 994
  10. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 655
  11. 2021KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3Dcited by 570
  12. 2022DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETRcited by 569
26 more
  1. 2022BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detectioncited by 568
  2. 2022PETR: Position Embedding Transformation for Multi-View 3D Object Detectioncited by 550
  3. 2016Semantic Scene Completion from a Single Depth Imagecited by 468
  4. 2021Conditional DETR for Fast Training Convergencecited by 422
  5. 2023Tri-Perspective View for Vision-Based 3D Semantic Occupancy Predictioncited by 404
  6. 2021MonoScene: Monocular 3D Semantic Scene Completioncited by 357
  7. 2022PETRv2: A Unified Framework for 3D Perception from Multi-Camera Imagescited by 351
  8. 2023SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Drivingcited by 310
  9. 2023VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completioncited by 306
  10. 2023OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Predictioncited by 287
  11. 2021FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Camerascited by 239
  12. 2020Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completioncited by 222
  13. 2022MetaFormer Baselines for Visioncited by 131
  14. 2017Learning non-maximum suppressioncited by 112
  15. 2020S3CNet: A Sparse Semantic Scene Completion Network for LiDAR Point Cloudscited by 102
  16. 2023Symphonize 3D Semantic Scene Completion with Contextual Instance Queriescited by 88
  17. 2023OccDepth: A Depth-Aware Method for 3D Semantic Scene Completioncited by 85
  18. 2021MobileStereoNet: Towards Lightweight Deep Networks for Stereo Matchingcited by 82
  19. 2023SCPNet: Semantic Scene Completion on Point Cloudcited by 80
  20. 2023SSCBench: A Large-Scale 3D Semantic Scene Completion Benchmark for Autonomous Drivingcited by 72
  21. 2024Context and Geometry Aware Voxel Transformer for Semantic Scene Completioncited by 50
  22. 2024MonoOcc: Digging into Monocular Semantic Occupancy Predictioncited by 43
  23. 2024Not All Voxels Are Equal: Hardness-Aware Semantic Scene Completion with Self-Distillationcited by 43
  24. 2021Semantic Segmentation-assisted Scene Completion for LiDAR Point Cloudscited by 37
  25. 2024Hierarchical Temporal Context Learning for Camera-based Semantic Scene Completioncited by 32
  26. 2023Bridging Stereo Geometry and BEV Representation with Reliable Mutual Interaction for Semantic Scene Completioncited by 21

Built on by

Cited by year (2026 to 7 Oct)

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

4 papers.

  1. 2025VoxDet: Rethinking 3D Semantic Occupancy Prediction as Dense Object Detectioncited by 12
  2. 2025OccuFly: A 3D Vision Benchmark for Semantic Scene Completion from the Aerial Perspectivecited by 5
  3. 2026AdaSFormer: Adaptive Serialized Transformers for Monocular Semantic Scene Completion from Indoor Environmentscited by 3
  4. 2026Sparsity-Aware Voxel Attention and Foreground Modulation for 3D Semantic Scene Completioncited by 0