Research map / 3D vision / 3D generation
FDR-Occ: Factorized Dense Routing for Full-Spectrum 3D Occupancy Prediction
Dubing Chen, Huan Zheng, Tianyi Yan, Yucheng Zhou, Runzhou Tao, Zhongying Qiu, Jianfei Yang, Shen Jianbing
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 FDR global pathway alongside LSS local pathway (ablation) | FDR-Occ · Occ3D-nuScenes ablation | mIoU: 37.0 -> 38.1 | Improved |
| add soft geometric hint to FDR routing weight generation (ablation) | FDR · Occ3D-nuScenes ablation | mIoU: 37.7 -> 38.1 | Improved |
| use tri-perspective representation instead of BEV only (ablation) | FDR-Occ · Occ3D-nuScenes ablation | mIoU: 37.7 -> 38.1 | Improved |
| use element-wise addition instead of adaptive weighting (ablation) | FDR-Occ · Occ3D-nuScenes ablation | mIoU: 38.0 -> 38.1 | No clear effect |
| fuse early on BEV plane rather than late after 3D encoder (ablation) | FDR-Occ · Occ3D-nuScenes ablation | mIoU: 37.7 -> 38.1 | Improved |
| use progressive 3-stage schedule 10-5-4 instead of 2 stages (ablation) | FDR · Occ3D-nuScenes ablation | mIoU: 37.4 -> 38.1 | Improved |
| use progressive expansion 10-5-4 instead of delayed expansion (ablation) | FDR · Occ3D-nuScenes ablation | mIoU: 37.7 (4-5-10) / 37.9 (10-10-2) -> 38.1 | Improved |
| use FDR-Occ instead of explicit-projection methods without camera parameters | FDR-Occ · Occ3D-nuScenes uncalibrated | mIoU: 12.0 (FB-Occ) -> 28.0 | Improved |
| use FDR-Occ instead of ALOcc-3D | FDR-Occ · Occ3D-Waymo | mIoU: 30.03 -> 31.25 | Improved |
| use FDR-Occ instead of CausalOcc | FDR-Occ · Occ3D-nuScenes single-frame | mIoU: 40.9 -> 41.2 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- COTR — COTR: Correspondence Transformer for Matching Across Images (ICCV 2021) · better on 3 of 3 shared results
- ProtoOcc — ProtoOcc: Accurate, Efficient 3D Occupancy Prediction Using Dual Branch Encoder-Prototype Query Decoder (AAAI 2025) · better on 1 of 1 shared result
- CVT-Occ — CVT-Occ: Cost Volume Temporal Fusion for 3D Occupancy Prediction (ECCV 2024) · better on 1 of 1 shared result
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
- OctOcc: High-Resolution 3D Occupancy Prediction with Octree (AAAI 2024 · similarity 0.88)
- Spatiotemporal Decoupling for Efficient Vision-Based Occupancy Forecasting (CVPR 2025 · similarity 0.88)
- 3D Occupancy Prediction with Low-Resolution Queries via Prototype-aware View Transformation (CVPR 2025 · similarity 0.87)
- ODG: Occupancy Prediction Using Dual Gaussians (NeurIPS 2025 · similarity 0.87)
- OccMamba: Semantic Occupancy Prediction with State Space Models (CVPR 2025 · similarity 0.87)
- Achieving Speed-Accuracy Balance in Vision-based 3D Occupancy Prediction via Geometric-Semantic Disentanglement (AAAI 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.
