Research map / 3D vision / 3D generation
UniOcc: A Unified Benchmark for Occupancy Forecasting and Prediction in Autonomous Driving
Yuping Wang, Xiangyu Huang, Xiaokang Sun, Mingxuan Yan, Shuo Xing, Zhengzhong Tu, Jiachen Li
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 voxel-level flow input and flow decoder | OccWorld · nuScenes forecasting | mIoU_geo at 0s: 66.79 -> 70.64 | Improved |
| add voxel-level flow input and flow decoder | OccWorld · nuScenes forecasting | IoU_bg: 53.27 -> 59.56 | Improved |
| add voxel-level flow input and flow decoder | OccWorld · Waymo forecasting | mIoU_geo at 0s: 68.24 -> 71.35 | Improved |
| use object-level flow instead of none | OccWorld · nuScenes forecasting | mIoU_geo at 0s: 66.79 -> 65.41 | No clear effect |
| use object-level flow instead of none | OccWorld · Waymo forecasting | IoU_bg: 56.06 -> 55.56 | No clear effect |
| train on Waymo instead of nuScenes, test on nuScenes | OccWorld · nuScenes forecasting | mIoU_geo at 0s: 70.64 -> 63.22 | Hurt |
| add Waymo to nuScenes training data | OccWorld · nuScenes forecasting | mIoU_geo at 3s: 19.06 -> 20.15 | Improved |
| add CARLA to nuScenes training data | OccWorld · nuScenes forecasting | IoU_bg: 59.56 -> 55.07 | Hurt |
| add CARLA to nuScenes training data | OccWorld · nuScenes forecasting | P_car: 82.57 -> 82.97 | No clear effect |
| add CARLA to Waymo training data | OccWorld · Waymo forecasting | IoU_geo at 1s: 36.04 -> 42.54 | Improved |
| use highway-only CARLA instead of full-speed CARLA when mixing with nuScenes (ablation) | OccWorld · nuScenes forecasting | IoU_bg: 55.07 -> 61.40 | Improved |
| use highway-only CARLA instead of full-speed CARLA when mixing with nuScenes (ablation) | OccWorld · nuScenes forecasting | IoU_car: 77.87 -> 85.59 | Improved |
Closest papers by meaning
- Cam4DOcc: Benchmark for Camera-Only 4D Occupancy Forecasting in Autonomous Driving Applications (CVPR 2024 · similarity 0.93)
- OccProphet: Pushing the Efficiency Frontier of Camera-Only 4D Occupancy Forecasting with an Observer-Forecaster-Refiner Framework (ICLR 2025 · similarity 0.92)
- Driving in the Occupancy World: Vision-Centric 4D Occupancy Forecasting and Planning via World Models for Autonomous Driving (AAAI 2025 · similarity 0.91)
- OPUS: Occupancy Prediction Using a Sparse Set (NeurIPS 2024 · similarity 0.90)
- COME: Adding Scene-Centric Forecasting Control to Occupancy World Model (NeurIPS 2025 · similarity 0.90)
- UnO: Unsupervised Occupancy Fields for Perception and Forecasting (CVPR 2024 · 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.
