Research map / 3D vision / Gaussian splatting
VAD-GS: Visibility-Aware Densification for 3D Gaussian Splatting in Dynamic Urban Scenes
Yikang Zhang, Rui Fan
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 voxel visibility reasoning (with MVS densification) (ablation) | VAD-GS · nuScenes | PSNR: 23.79 -> 24.51 | Improved |
| add diversity-aware view selection (ablation) | VAD-GS · nuScenes | PSNR: 23.92 -> 24.51 | Improved |
| add geometric (normal and depth) losses (ablation) | VAD-GS · nuScenes | PSNR / LPIPS: PSNR 24.59 -> 24.51; PSNR* 22.78 -> 23.16; LPIPS 0.194 -> 0.199 | Mixed |
| use VAD-GS instead of StreetGS | Waymo Open · Waymo Open (8 sequences) | PSNR: 34.61 -> 35.59 | Improved |
| use VAD-GS instead of PVG on a linear-trajectory scene | nuScenes Scene 05 · nuScenes Scene 05 | PSNR: 20.76 -> 20.06 | 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 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
- D$^2$GS: Dense Depth Regularization for LiDAR-free Urban Scene Reconstruction (NeurIPS 2025 · similarity 0.92)
- CityGaussianV2: Efficient and Geometrically Accurate Reconstruction for Large-Scale Scenes (ICLR 2025 · similarity 0.92)
- Horizon-GS: Unified 3D Gaussian Splatting for Large-Scale Aerial-to-Ground Scenes (CVPR 2025 · similarity 0.91)
- EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis (CVPR 2025 · similarity 0.91)
- VA-GS: Enhancing the Geometric Representation of Gaussian Splatting via View Alignment (NeurIPS 2025 · similarity 0.91)
- Evolving High-Quality Rendering and Reconstruction in a Unified Framework with Contribution-Adaptive Regularization (CVPR 2025 · similarity 0.90)
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.
