Research map / 3D vision / 3D generation
LiSTAR: Ray-Centric World Models for 4D LiDAR Sequences in Autonomous Driving
Pei Liu, Songtao Wang, Lang Zhang, Xinyue Peng, Yuandong Lyu, Jiaxin Deng, Songxin lu, Weiliang Ma, Xueyang Zhang, Yifei Zhan, Kun Zhan, Jun Ma
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 |
|---|---|---|---|
| use HCS voxelization instead of Cartesian (ablation) | LiSTAR VQ-VAE · nuScenes reconstruction | IoU: 0.414 -> 0.554 | Improved |
| use HCS voxelization instead of Polar (ablation) | LiSTAR VQ-VAE · nuScenes reconstruction | IoU: 0.476 -> 0.554 | Improved |
| use HCS voxelization instead of Cartesian (ablation) | LiSTAR VQ-VAE · nuScenes reconstruction | MMD (1e-4): 0.475 -> 0.065 | Improved |
| add Spatial Ray-Centric Attention (SRA) (ablation) | LiSTAR VQ-VAE · nuScenes reconstruction | IoU: 0.503 -> 0.554 | Improved |
| add Spatial Ray-Centric Attention (SRA) (ablation) | LiSTAR VQ-VAE · nuScenes reconstruction | MMD (1e-4): 0.116 -> 0.065 | Improved |
| add Cyclic-Shifted Temporal Causal Attention (CSTA) on top of SRA (ablation) | LiSTAR VQ-VAE · nuScenes reconstruction | IoU: 0.554 -> 0.583 | Improved |
| replace OpenDWM with LiSTAR for reconstruction | LiSTAR · nuScenes reconstruction | IoU: 0.441 -> 0.583 | Improved |
| replace Copilot4D with LiSTAR for 1s prediction | LiSTAR · nuScenes 1s prediction (70m ROI) | L1 Med: 0.10 -> 0.05 | Improved |
| replace OpenDWM with LiSTAR for generation | LiSTAR · nuScenes generation | MMD (1e-4): 41.14 -> 9.94 | Improved |
| replace OpenDWM with LiSTAR for generation | LiSTAR · nuScenes generation | JSD: 0.31 -> 0.30 | No clear effect |
Closest papers by meaning
- LiDARCrafter: Dynamic 4D World Modeling from LiDAR Sequences (AAAI 2026 · similarity 0.93)
- LiDAR-RT: Gaussian-based Ray Tracing for Dynamic LiDAR Re-simulation (CVPR 2025 · similarity 0.87)
- Genesis: Multimodal Driving Scene Generation with Spatio-Temporal and Cross-Modal Consistency (NeurIPS 2025 · similarity 0.87)
- Outdoor Scene Extrapolation with Hierarchical Generative Cellular Automata (CVPR 2024 · similarity 0.87)
- NeRF-LiDAR: Generating Realistic LiDAR Point Clouds with Neural Radiance Fields (AAAI 2024 · similarity 0.86)
- LiDAR4D: Dynamic Neural Fields for Novel Space-time View LiDAR Synthesis (CVPR 2024 · similarity 0.86)
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.
