Research map / 3D vision / Gaussian splatting
GaussRender: Learning 3D Occupancy with Gaussian Rendering
Loick Chambon, Eloi Zablocki, Alexandre Boulch, Mickael Chen, Matthieu Cord
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add GaussRender to TPVFormer | TPVFormer · SurroundOcc-nuScenes val | mIoU: 17.10 -> 20.85 | Improved |
| add GaussRender to SurroundOcc | SurroundOcc · SurroundOcc-nuScenes val | mIoU: 20.30 -> 20.82 | Improved |
| add GaussRender to TPVFormer | TPVFormer · Occ3D-nuScenes val | mIoU: 27.83 -> 30.48 | Improved |
| add GaussRender to SurroundOcc | SurroundOcc · SSCBench-KITTI360 test | IoU: 38.51 -> 38.62 | Improved |
| add GaussRender to Symphonies | Symphonies · SSCBench-KITTI360 test | mIoU: 17.82 -> 18.11 | Improved |
| add GaussRender to TPVFormer | TPVFormer · Occ3D-nuScenes val | RayIoU: 37.2 -> 38.3 | Improved |
| add GaussRender to SurroundOcc | SurroundOcc · Occ3D-nuScenes val | RayIoU: 35.5 -> 37.5 | Improved |
| use Elevated + Around cameras instead of sensor cameras (2D+3D) (ablation) | TPVFormer + GaussRender · Occ3D-nuScenes (20% subset) | mIoU: 25.9 -> 26.3 | Improved |
| use fully random cameras instead of sensor cameras (2D-only) (ablation) | TPVFormer + GaussRender · Occ3D-nuScenes (20% subset) | mIoU: 16.1 -> 6.9 | Hurt |
| use dynamic cameras instead of sensor cameras (2D-only) (ablation) | TPVFormer + GaussRender · Occ3D-nuScenes (20% subset) | mIoU: 16.1 -> 4.8 | Hurt |
| add depth rendering loss on camera view (ablation) | TPVFormer + GaussRender · SurroundOcc-nuScenes (20% subset) | mIoU: 14.3 -> 15.1 | Improved |
| add BEV camera loss (ablation) | TPVFormer + GaussRender · SurroundOcc-nuScenes (20% subset) | mIoU: 15.1 -> 15.6 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- SurroundOcc — SurroundOcc: Multi-camera 3D Occupancy Prediction for Autonomous Driving (ICCV 2023) · better on 6 of 6 shared results
- GaussianFormerv2 — GaussianFormer: Scene as Gaussians for Vision-Based 3D Semantic Occupancy Prediction (ECCV 2024) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- ODG: Occupancy Prediction Using Dual Gaussians (NeurIPS 2025 · similarity 0.93)
- GaussianFormer-2: Probabilistic Gaussian Superposition for Efficient 3D Occupancy Prediction (CVPR 2025 · similarity 0.92)
- GaussianWorld: Gaussian World Model for Streaming 3D Occupancy Prediction (CVPR 2025 · similarity 0.92)
- GaussTR: Foundation Model-Aligned Gaussian Transformer for Self-Supervised 3D Spatial Understanding (CVPR 2025 · similarity 0.91)
- VoxelSplat: Dynamic Gaussian Splatting as an Effective Loss for Occupancy and Flow Prediction (CVPR 2025 · similarity 0.90)
- QuadricFormer: Scene as Superquadrics for 3D Semantic Occupancy Prediction (NeurIPS 2025 · similarity 0.90)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
