Research map / 3D vision / Gaussian splatting
Leveraging 2D Priors and SDF Guidance for Urban Scene Rendering
Siddharth Tourani, Jayaram Reddy, Akash Kumbar, Satyajit Tourani, Nishant Goyal, Madhava Krishna, N Dinesh Reddy, Muhammad Haris Khan
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 SDF guidance for Gaussian primitive distribution (ablation) | UGSDF · NOTR human category | PSNR: 22.47 -> 27.89 | Improved |
| add SDF guidance for Gaussian primitive distribution (ablation) | UGSDF · NOTR vehicle category | PSNR: 22.27 -> 30.34 | Improved |
| use dense representation instead of sparse (ablation) | UGSDF · NOTR human category | PSNR: 24.82 -> 27.89 | Improved |
| use dense representation instead of sparse (ablation) | UGSDF · NOTR vehicle category | PSNR: 25.14 -> 30.34 | Improved |
| add Gaussian-guided point sampling for SDF (ablation) | UGSDF · NOTR human category | PSNR: 25.82 -> 27.89 | Improved |
| add Gaussian-guided point sampling for SDF (ablation) | UGSDF · NOTR vehicle category | PSNR: 27.83 -> 30.34 | Improved |
| add LiDAR input | UGSDF · Waymo/NOTR dynamic-32 | novel view synthesis PSNR: 30.32 -> 30.63 | Improved |
| add LiDAR input | UGSDF · Waymo/NOTR dynamic-32 | scene reconstruction PSNR: 33.88 -> 33.98 | No clear effect |
| use UGSDF instead of OmniRe on humans | UGSDF vs OmniRe · NOTR human category | scene reconstruction PSNR: 28.15 -> 27.89 | Hurt |
| use own tracking boxes instead of GT boxes | UGSDF · KITTI MOT tracking evaluation | PSNR: 31.34 -> 30.55 | 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.
- OmniRe — OmniRe: Omni Urban Scene Reconstruction (ICLR 2025) · better on 8 of 8 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
- EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis (CVPR 2025 · similarity 0.90)
- Motion Decoupled 3D Gaussian Splatting for Dynamic Object Representation (AAAI 2025 · similarity 0.90)
- D$^2$GS: Dense Depth Regularization for LiDAR-free Urban Scene Reconstruction (NeurIPS 2025 · similarity 0.90)
- CityGaussianV2: Efficient and Geometrically Accurate Reconstruction for Large-Scale Scenes (ICLR 2025 · similarity 0.89)
- HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splatting (CVPR 2024 · similarity 0.89)
- Horizon-GS: Unified 3D Gaussian Splatting for Large-Scale Aerial-to-Ground Scenes (CVPR 2025 · similarity 0.89)
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.
