Research map / 3D vision / Gaussian splatting
SimULi: Real-Time LiDAR and Camera Simulation with Unscented Transforms
Haithem Turki, Qi Wu, Xin Kang, Janick Martinez Esturo, Shengyu Huang, Ruilong Li, Zan Gojcic, Riccardo de Lutio
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 factorized camera/LiDAR Gaussian sets with anchoring loss (vs single set, depth loss 0.01) (ablation) | SimULi · PandaSet NVS (ablation avg) | PSNR (dB): 26.39 -> 27.12 | Improved |
| add factorized Gaussians (LiDAR speed vs single set) (ablation) | SimULi · PandaSet NVS (ablation avg) | LiDAR speed (MR/s): 4.97 -> 11.02 | Improved |
| add LiDAR anchoring vs camera-only (lambda_d=0) (ablation) | SimULi · PandaSet NVS (ablation avg) | Chamfer distance: 6.248 -> 0.331 | Improved |
| increase direct LiDAR depth loss weight from 0.001 to 0.1 in unified set (ablation) | single-set baseline · PandaSet NVS (ablation avg) | PSNR (dB): 26.70 -> 25.78; CD 0.718 -> 0.393 | Mixed |
| add bilateral grid (ablation) | SimULi · PandaSet NVS (ablation avg) | PSNR (dB): 25.99 -> 27.12 | Improved |
| add environment map (ablation) | SimULi · PandaSet NVS (ablation avg) | PSNR (dB): 26.81 -> 27.12 | Improved |
| add bilateral grid (LiDAR speed) (ablation) | SimULi · PandaSet NVS (ablation avg) | LiDAR speed (MR/s): 12.07 -> 11.02 | No clear effect |
| add ray-based culling (ablation) | SimULi · LiDAR render kernel | time (ms): 5.17 -> 4.71 | Improved |
| tune max points per tile M and elevation tiles to 32 and 16 (ablation) | SimULi · LiDAR tiling | MR/s: 6.49 -> 15.75 | Improved |
| use SimULi vs SplatAD on Waymo Dynamic | SimULi · Waymo Dynamic | PSNR (dB): 30.60 -> 32.35 | Improved |
| use SimULi vs LiDAR-only LiDAR-RT on Waymo Interp. | SimULi · Waymo Interp. | RayDrop accuracy: 0.962 -> 0.944 | Hurt |
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.
- SplatAD — SplatAD: Real-Time Lidar and Camera Rendering with 3D Gaussian Splatting for Autonomous Driving (CVPR 2025) · better on 4 of 4 shared results
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
- SplatAD: Real-Time Lidar and Camera Rendering with 3D Gaussian Splatting for Autonomous Driving (CVPR 2025 · similarity 0.90)
- LiDAR-RT: Gaussian-based Ray Tracing for Dynamic LiDAR Re-simulation (CVPR 2025 · similarity 0.90)
- GenAssets: Generating in-the-wild 3D Assets in Latent Space (CVPR 2025 · similarity 0.88)
- NeRF-LiDAR: Generating Realistic LiDAR Point Clouds with Neural Radiance Fields (AAAI 2024 · similarity 0.87)
- ProtoCar: Learning 3D Vehicle Prototypes from Single-View and Unconstrained Driving Scene Images (AAAI 2025 · similarity 0.87)
- LidaRF: Delving into Lidar for Neural Radiance Field on Street Scenes (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.
