mlsanityData to 14 Oct 2026

Gau-Occ: Geometry-Completed Gaussians for Multi-Modal 3D Occupancy Prediction

arXiv 2603.22852 ↗First posted 24 Mar 2026cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

3D semantic occupancy prediction is crucial for autonomous driving. While multi-modal fusion improves accuracy over vision-only methods, it typically relies on computationally expensive dense voxel or BEV tensors. We present Gau-Occ, a multi-modal framework that bypasses dense volumetric processing by modeling the scene as a compact collection of semantic 3D Gaussians. To ensure geometric completeness, we propose a LiDAR Completion Diffuser (LCD) that recovers missing structures from sparse LiDAR to initialize robust Gaussian anchors. Furthermore, we introduce Gaussian Anchor Fusion (GAF), which efficiently integrates multi-view image semantics via geometry-aligned 2D sampling and cross-modal alignment. By refining these compact Gaussian descriptors, Gau-Occ captures both spatial consistency and semantic discriminability. Extensive experiments across challenging benchmarks demonstrate that Gau-Occ achieves state-of-the-art performance with significant computational efficiency.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 53 of its 58 references that are in the map. First posted on arXiv 24 Mar 2026.

Builds on

53 of 58 references.

References · 53

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  3. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  4. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,333
  5. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  6. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,218
  7. 2020Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3Dcited by 1,044
  8. 2022BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representationcited by 850
  9. 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 713
  10. 2021KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3Dcited by 575
  11. 2016Semantic Scene Completion from a Single Depth Imagecited by 472
  12. 2022TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformerscited by 466
38 more
  1. 2019PointPainting: Sequential Fusion for 3D Object Detectioncited by 449
  2. 2023Tri-Perspective View for Vision-Based 3D Semantic Occupancy Predictioncited by 409
  3. 2021MonoScene: Monocular 3D Semantic Scene Completioncited by 363
  4. 2023Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Drivingcited by 332
  5. 2023SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Drivingcited by 316
  6. 2023VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completioncited by 313
  7. 2022BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervisioncited by 302
  8. 2023OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Predictioncited by 293
  9. 2021FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Camerascited by 239
  10. 2023OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perceptioncited by 221
  11. 2020LMSCNet: Lightweight Multiscale 3D Semantic Completioncited by 188
  12. 2023FB-OCC: 3D Occupancy Prediction based on Forward-Backward View Transformationcited by 165
  13. 2019MVX-Net: Multimodal VoxelNet for 3D Object Detectioncited by 163
  14. 2024GaussianFormer: Scene as Gaussians for Vision-Based 3D Semantic Occupancy Predictioncited by 157
  15. 2020Anisotropic Convolutional Networks for 3D Semantic Scene Completioncited by 127
  16. 2023PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentationcited by 115
  17. 2023FlashOcc: Fast and Memory-Efficient Occupancy Prediction via Channel-to-Height Plugincited by 103
  18. 2023COTR: Compact Occupancy TRansformer for Vision-based 3D Occupancy Predictioncited by 96
  19. 2023OccDepth: A Depth-Aware Method for 3D Semantic Scene Completioncited by 86
  20. 2024GaussianFormer-2: Probabilistic Gaussian Superposition for Efficient 3D Occupancy Predictioncited by 86
  21. 2023SSCBench: A Large-Scale 3D Semantic Scene Completion Benchmark for Autonomous Drivingcited by 75
  22. 2023MSeg3D: Multi-modal 3D Semantic Segmentation for Autonomous Drivingcited by 68
  23. 2024GaussianWorld: Gaussian World Model for Streaming 3D Occupancy Predictioncited by 67
  24. 2024GaussianOcc: Fully Self-supervised and Efficient 3D Occupancy Estimation with Gaussian Splattingcited by 50
  25. 2018Two Stream 3D Semantic Scene Completioncited by 48
  26. 2024Co-Occ: Coupling Explicit Feature Fusion with Volume Rendering Regularization for Multi-Modal 3D Semantic Occupancy Predictioncited by 48
  27. 2024OccMamba: Semantic Occupancy Prediction with State Space Modelscited by 30
  28. 2023RadOcc: Learning Cross-Modality Occupancy Knowledge through Rendering Assisted Distillationcited by 27
  29. 2025STCOcc: Sparse Spatial-Temporal Cascade Renovation for 3D Occupancy and Scene Flow Predictioncited by 23
  30. 2024ALOcc: Adaptive Lifting-Based 3D Semantic Occupancy and Cost Volume-Based Flow Predictionscited by 20
  31. 2023LiDAR-Camera Panoptic Segmentation via Geometry-Consistent and Semantic-Aware Alignmentcited by 18
  32. 2025GaussRender: Learning 3D Occupancy with Gaussian Renderingcited by 18
  33. 2024DAOcc: 3D Object Detection Assisted Multi-Sensor Fusion for 3D Occupancy Predictioncited by 15
  34. 2025AutoOcc: Automatic Open-Ended Semantic Occupancy Annotation via Vision-Language Guided Gaussian Splattingcited by 14
  35. 2025GaussianFormer3D: Multi-Modal Gaussian-based Semantic Occupancy Prediction with 3D Deformable Attentioncited by 14
  36. 2026TokenSplat: Token-aligned 3D Gaussian Splatting for Feed-forward Pose-free Reconstructioncited by 14
  37. 2024OccFusion: Depth Estimation Free Multi-sensor Fusion for 3D Occupancy Predictioncited by 13
  38. 2025Micro-macro Wavelet-based Gaussian Splatting for 3D Reconstruction from Unconstrained Imagescited by 10

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026GraphBEV++: Multi-Modal Feature Alignment for Autonomous Drivingcited by 0