Research map / 3D vision / 3D generation
SurroundOcc: Multi-camera 3D Occupancy Prediction for Autonomous Driving
Yi Wei, Linqing Zhao, Wenzhao Zheng, Zheng Zhu, Jie Zhou, Jiwen Lu
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 |
|---|---|---|---|
| supervise with dense occupancy labels instead of sparse LiDAR points (ablation) | SurroundOcc · nuScenes val | SSC mIoU: 12.17 -> 20.30 | Improved |
| densify multi-frame sparse occupancy labels with Poisson reconstruction and NN (ablation) | SurroundOcc labels · nuScenes val | SSC mIoU: 18.83 -> 20.30 | Improved |
| use 3D volume cross-view attention instead of averaging multi-camera features (ablation) | SurroundOcc · nuScenes val | SSC mIoU: 17.34 -> 20.30 | Improved |
| use 3D volume queries instead of BEV queries in cross-view attention (ablation) | SurroundOcc · nuScenes val | SSC mIoU: 18.94 -> 20.30 | Improved |
| add multi-scale skip connection structure (ablation) | SurroundOcc · nuScenes val | SSC mIoU: 18.22 -> 20.30 | Improved |
| add multi-scale supervision with decayed loss weights (ablation) | SurroundOcc · nuScenes val | SSC mIoU: 19.73 -> 20.30 | Improved |
| train TPVFormer with dense occupancy labels instead of sparse LiDAR points | TPVFormer · nuScenes val | SC IoU / SSC mIoU: SC IoU 11.51 -> 30.86; SSC mIoU 11.66 -> 17.10 | Improved |
| SurroundOcc applied to monocular SemanticKITTI without monocular-specific design | SurroundOcc · SemanticKITTI test | SSC mIoU: 11.26 -> 11.86 (vs TPVFormer) | Improved |
| SurroundOcc versus BEVFormer in efficiency | SurroundOcc · nuScenes inference, RTX 3090 | latency/memory: 0.31 -> 0.34 s; 4.5 -> 5.9 G | Hurt |
Later papers that compared with this method
16 later accepted papers report SurroundOcc as a baseline in their results tables; 14 of them report a better number on most of the results they share with it.
- An Instance-Centric Panoptic Occupancy Prediction Benchmark for Autonomous Driving (CVPR 2026 · better on 2 of 2 shared results)
- AdaSFormer: Adaptive Serialized Transformers for Monocular Semantic Scene Completion from Indoor Environments (CVPR 2026 · better on 2 of 2 shared results)
- Generalizing Visual Geometry Priors to Sparse Gaussian Occupancy Prediction (CVPR 2026 · better on 2 of 2 shared results)
- DLWM: Dual Latent World Models enable Holistic Gaussian-centric Pre-training in Autonomous Driving (CVPR 2026 · better on 1 of 1 shared result)
- GaussRender: Learning 3D Occupancy with Gaussian Rendering (ICCV 2025 · better on 6 of 6 shared results)
- AutoOcc: Automatic Open-Ended Semantic Occupancy Annotation via Vision-Language Guided Gaussian Splatting (ICCV 2025 · better on 5 of 5 shared results)
- EmbodiedOcc: Embodied 3D Occupancy Prediction for Vision-based Online Scene Understanding (ICCV 2025 · better on 4 of 4 shared results)
- GaussianFormer-2: Probabilistic Gaussian Superposition for Efficient 3D Occupancy Prediction (CVPR 2025 · better on 2 of 2 shared results)
8 more not listed.
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.
- MonoScene — MonoScene: Monocular 3D Semantic Scene Completion (CVPR 2022) · better on 2 of 2 shared results
- TransformerFusion — TransformerFusion: Monocular RGB Scene Reconstruction using Transformers (NeurIPS 2021) · 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 0.93)
- SelfOcc: Self-Supervised Vision-Based 3D Occupancy Prediction (CVPR 2024 · similarity 0.93)
- CSV-Occ: Fusing Multi-frame Alignment for Occupancy Prediction with Temporal Cross State Space Model and Central Voting Mechanism (ICML 2025 · similarity 0.91)
- ViPOcc: Leveraging Visual Priors from Vision Foundation Models for Single-View 3D Occupancy Prediction (AAAI 2025 · similarity 0.91)
- ODG: Occupancy Prediction Using Dual Gaussians (NeurIPS 2025 · similarity 0.91)
- Achieving Speed-Accuracy Balance in Vision-based 3D Occupancy Prediction via Geometric-Semantic Disentanglement (AAAI 2025 · similarity 0.91)
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.
