Research map / 3D vision / Gaussian splatting
UniMGS: Unifying Mesh and 3D Gaussian Splatting with Single-Pass Rasterization and Proxy-Based Deformation
Zeyu Xiao, Mingyang Sun, Yimin Cong, Lintao Wang, Dongliang Kou, Zhenyi Wu, Dingkang Yang, Peng Zhai, Zeyu Wang, Lihua Zhang
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 |
|---|---|---|---|
| bind Gaussians to 8 faces via bounding-box corners instead of single face (ablation) | UniMGS · NeRF-Synthetic deformation | PSNR: 28.23 -> 28.43 | Improved |
| bounding-box binding vs single-face binding (ablation) | UniMGS · NeRF-Synthetic deformation | LPIPS: 0.051 -> 0.048 | Improved |
| Gaussian-centric binding via ray casting instead of mesh-centric binding | UniMGS · NeRF-Synthetic deformation | PSNR: 27.21 -> 28.43 (vs GaussianMesh) | Improved |
| Gaussian-centric binding instead of Mani-GS | UniMGS · NeRF-Synthetic deformation | PSNR: 23.76 -> 28.43 | Improved |
| Gaussian-centric binding keeps trained 3DGS unchanged | UniMGS · NeRF-Synthetic deformation | Gaussian count: 989K -> 275K (vs GaussianMesh) | Improved |
| single-pass rasterization of meshes with 3DGS instead of ray tracing (3DGUT) | UniMGS · garden + low-poly meshes | render time: 3DGUT slows 3.4x with meshes, UniMGS stays stable | Improved |
| treat only depth-adjacent triangles as one MSAA entity (ablation) | UniMGS · mesh+Gaussian scenes | visual artifacts | Improved |
| Gaussian-centric binding with flawed proxy mesh (NeuS2 cup) | UniMGS · proxy mesh robustness | visual quality | 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.
- Mani-GS — Mani-GS: Gaussian Splatting Manipulation with Triangular Mesh (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
- FlashGS: Efficient 3D Gaussian Splatting for Large-scale and High-resolution Rendering (CVPR 2025 · similarity 0.91)
- UVGS: Reimagining Unstructured 3D Gaussian Splatting using UV Mapping (CVPR 2025 · similarity 0.91)
- FlexGS: Train Once, Deploy Everywhere with Many-in-One Flexible 3D Gaussian Splatting (CVPR 2025 · similarity 0.90)
- Steepest Descent Density Control for Compact 3D Gaussian Splatting (CVPR 2025 · similarity 0.90)
- GaussianPro: 3D Gaussian Splatting with Progressive Propagation (ICML 2024 · similarity 0.90)
- Gaussian Herding across Pens: An Optimal Transport Perspective on Global Gaussian Reduction for 3DGS (NeurIPS 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.
