Research map / Point clouds / Shape and surface completion
Learning to Generate Realistic LiDAR Point Clouds
Vlas Zyrianov, Xiyue Zhu, Shenlong Wang
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 coordinate encoding (ablation) | LiDARGen · KITTI-360 | FRD: 2422.3 -> 2251.1 | Improved |
| add coordinate encoding (ablation) | LiDARGen · KITTI-360 | MMD: 7.60 x 10^-4 -> 3.94 x 10^-4 | Improved |
| add circular convolution (ablation) | LiDARGen · KITTI-360 | FRD: 2251.1 -> 2040.1 | Improved |
| add circular convolution (ablation) | LiDARGen · KITTI-360 | MMD: 3.94 x 10^-4 -> 3.87 x 10^-4 | No clear effect |
| use LiDARGen instead of Projected GAN | LiDARGen · KITTI-360 | FRD: 2117.2 -> 2040.1 | Improved |
| use LiDARGen instead of Projected GAN | LiDARGen · KITTI-360 | MMD (BEV): 3.47 x 10^-4 -> 3.87 x 10^-4 | Hurt |
| use LiDARGen instead of Projected GAN | LiDARGen · nuScenes | MMD (BEV): 6e-5 -> 2e-3 | Hurt |
| use LiDARGen densification instead of nearest neighbor | LiDARGen · KITTI-360 densification | MAE: 2.18 -> 1.23 | Improved |
| use LiDARGen densification instead of nearest neighbor | LiDARGen · KITTI-360 RangeNet++ segmentation | per-point accuracy: 0.546 -> 0.608 | Improved |
| use LiDARGen densification instead of nearest neighbor | LiDARGen · KITTI-360 RangeNet++ segmentation | IoU: 0.394 -> 0.449 | Improved |
Closest papers by meaning
- WeatherGen: A Unified Diverse Weather Generator for LiDAR Point Clouds via Spider Mamba Diffusion (CVPR 2025 · similarity 0.89)
- GS-LiDAR: Generating Realistic LiDAR Point Clouds with Panoramic Gaussian Splatting (ICLR 2025 · similarity 0.88)
- LiFi: LiDAR Generation from Multi-View Images via Geometric and Semantic Collaborative Guidance (NeurIPS 2026 · similarity 0.87)
- LiDAR-Net: A Real-scanned 3D Point Cloud Dataset for Indoor Scenes (CVPR 2024 · similarity 0.87)
- Towards Realistic Scene Generation with LiDAR Diffusion Models (CVPR 2024 · similarity 0.87)
- LiSu: A Dataset and Method for LiDAR Surface Normal Estimation (CVPR 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.
