Research map / Point clouds / Point cloud classification
DriveLiDAR4D: Sequential and Controllable LiDAR Scene Generation for Autonomous Driving
Kaiwen Cai, Xinze Liu, Xia Zhou, Hengtong Hu, Jie Xiang, Luyao Zhang, Xueyang Zhang, Kun Zhan, Yifei Zhan, Xianpeng Lang
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 road sketch condition (ablation) | DriveLiDAR4D · nuScenes val | FRD: 210.55 -> 178.24 | Improved |
| add scene caption on top of road sketch (ablation) | DriveLiDAR4D · nuScenes val | FRD: 178.24 -> 175.17 | Improved |
| add road sketch condition (ablation) | DriveLiDAR4D · nuScenes val | MMD (x10^4): 1.84 -> 0.85 | Improved |
| add scene caption on top of road sketch (ablation) | DriveLiDAR4D · nuScenes val | MMD (x10^4): 0.85 -> 0.85 | No clear effect |
| replace regular 2D conv with EST-Conv (Fourier features, circular padding, temporal 3D conv) (ablation) | LiDAR4DNet · nuScenes val sequential | FVD: 29.50 -> 17.28 | Improved |
| replace regular 2D conv with EST-Conv (ablation) | LiDAR4DNet · nuScenes val sequential | FRD: 318.05 -> 311.38 | Improved |
| add EST-Trans at bottleneck (ablation) | LiDAR4DNet · nuScenes val sequential | FRD: 311.38 -> 292.28 | Improved |
| add EST-Trans at bottleneck (ablation) | LiDAR4DNet · nuScenes val sequential | FVD: 17.28 -> 14.86 | Improved |
| add object priors from synthesized object point clouds (ablation) | DriveLiDAR4D · nuScenes val car detection on generated scenes | mAP: 0.123 -> 0.407 | Improved |
| DriveLiDAR4D vs RangeLDM, unconditional on KITTI-360 | DriveLiDAR4D · KITTI-360 test | MMD (x10^4): 0.75 -> 3.31 | Hurt |
| DriveLiDAR4D vs RangeLDM, unconditional on nuScenes | DriveLiDAR4D · nuScenes val | FRD: 492.49 -> 210.55 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Text2LiDAR — Text2LiDAR: Text-guided LiDAR Point Clouds Generation via Equirectangular Transformer (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
- NeRF-LiDAR: Generating Realistic LiDAR Point Clouds with Neural Radiance Fields (AAAI 2024 · similarity 0.88)
- Genesis: Multimodal Driving Scene Generation with Spatio-Temporal and Cross-Modal Consistency (NeurIPS 2025 · similarity 0.88)
- GS-LiDAR: Generating Realistic LiDAR Point Clouds with Panoramic Gaussian Splatting (ICLR 2025 · similarity 0.88)
- SplatAD: Real-Time Lidar and Camera Rendering with 3D Gaussian Splatting for Autonomous Driving (CVPR 2025 · similarity 0.87)
- OLiDM: Object-aware LiDAR Diffusion Models for Autonomous Driving (AAAI 2025 · similarity 0.87)
- Towards Realistic Scene Generation with LiDAR Diffusion Models (CVPR 2024 · 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.
