Research map / 3D vision / 3D generation
Gaussian-based World Model: Gaussian Priors for Voxel-Based Occupancy Prediction and Future Motion Prediction
Tuo Feng, Wenguan Wang, Yi Yang
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 1st-stage self-supervised Gaussian pre-training (ablation) | GWM · Occ3D / nuScenes | Avg. mIoU (%): 8.25 -> 10.12 | Improved |
| add 1st-stage self-supervised Gaussian pre-training (ablation) | GWM · nuScenes | Avg. L2 error (m): 1.28 -> 1.13 | Improved |
| add 1st-stage self-supervised Gaussian pre-training (ablation) | GWM · nuScenes | PSNR: 24.58 -> 27.62 | Improved |
| use Gaussian representation instead of voxel-based FBOCC (ablation) | GWM · Occ3D | Avg. mIoU (%): 8.97 -> 10.12 | Improved |
| use Gaussian representation instead of voxel-based FBOCC (ablation) | GWM · nuScenes | Avg. L2 error (m): 1.27 -> 1.13 | Improved |
| use LiDAR priors instead of SfM priors (ablation) | GWM · Occ3D | Avg. mIoU (%): 8.61 -> 10.12 | Improved |
| use LiDAR priors instead of SfM priors (ablation) | GWM · nuScenes | Avg. L2 error (m): 1.21 -> 1.13 | Improved |
| add semantic map (ablation) | GWM · Occ3D | Avg. mIoU (%): 9.84 -> 10.12 | Improved |
| add semantic map (ablation) | GWM · nuScenes | Avg. collision rate (%): 0.61 -> 0.59 | Improved |
| use GWM instead of OccLLaMA-F | GWM · Occ3D | Avg. mIoU (%): 8.66 -> 10.12 | Improved |
| use GWM instead of OccLLaMA-F | GWM · nuScenes | Avg. collision rate (%): 0.70 -> 0.59 | Improved |
| use GWM instead of OccWorld-F on noisy occluded subset | GWM · nuScenes challenging subset | mIoU (%): 5.72 -> 9.14 | Improved |
Closest papers by meaning
- GaussianWorld: Gaussian World Model for Streaming 3D Occupancy Prediction (CVPR 2025 · similarity 0.92)
- GaussianFormer-2: Probabilistic Gaussian Superposition for Efficient 3D Occupancy Prediction (CVPR 2025 · similarity 0.89)
- GaussianFusion: Gaussian-Based Multi-Sensor Fusion for End-to-End Autonomous Driving (NeurIPS 2025 · similarity 0.89)
- ODG: Occupancy Prediction Using Dual Gaussians (NeurIPS 2025 · similarity 0.88)
- Driving in the Occupancy World: Vision-Centric 4D Occupancy Forecasting and Planning via World Models for Autonomous Driving (AAAI 2025 · similarity 0.88)
- GaussTR: Foundation Model-Aligned Gaussian Transformer for Self-Supervised 3D Spatial Understanding (CVPR 2025 · similarity 0.87)
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.
