Research map / 3D vision / Gaussian splatting
PATexGS: Perceptual-Adaptive Texture Scheduling for Visual Coherence in Textured Gaussian Splatting
Yuesong Wang, Dounian Ma, Xiaoyu Chen, Tao Guan
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 mipmap-based texture scheduling at 1/8 resolution (ablation) | PATexGS · Tanks&Temples 10% Gaussians, 1/8 resolution | PSNR: 21.15 -> 23.65 | Improved |
| add mipmap scheduling at full resolution (ablation) | PATexGS · Tanks&Temples 10% Gaussians, full resolution | PSNR: 23.41 -> 23.43 | No clear effect |
| add alpha-channel mipmap (ablation) | PATexGS · Tanks&Temples 10% Gaussians, 1/8 resolution | PSNR: 21.59 -> 23.65 | Improved |
| add RGB-channel mipmap (ablation) | PATexGS · Tanks&Temples 10% Gaussians, 1/8 resolution | PSNR: 23.35 -> 23.65 | Improved |
| use adaptive texture allocation instead of fixed 32x32 textures (ablation) | PATexGS · Tanks&Temples 10% Gaussians | PSNR: 23.02 -> 23.43 | Improved |
| use adaptive allocation instead of fixed 32x32 textures (storage) (ablation) | PATexGS · Tanks&Temples 10% Gaussians | storage (M): 223.0 -> 45 | Improved |
| use adaptive allocation instead of fixed texture of similar parameter count (ablation) | PATexGS · Tanks&Temples 10% Gaussians | PSNR: 23.29 -> 23.43 | Improved |
| apply adaptive allocation to BBSplat | BBSplat · Mip-NeRF360 (9 scenes), full Gaussians | PSNR: 26.92 -> 27.11 (Mip-NeRF360); 23.69 -> 24.10 (T&T); SSIM 0.786 -> 0.785 | Mixed |
| use PATexGS instead of 2DGS when only 1% of Gaussians are kept | 2DGS · Mip-NeRF360 (9 scenes), 1% Gaussians | PSNR: 22.64 -> 23.84 | Improved |
| use PATexGS instead of Mip Splatting at full Gaussians | Mip Splatting · Mip-NeRF360 (9 scenes), full Gaussians | PSNR: 27.79 -> 27.71 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- Mip Splatting — Mip-Splatting: Alias-free 3D Gaussian Splatting (CVPR 2024) · better on 1 of 2 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
- Perceptual-GS: Scene-adaptive Perceptual Densification for Gaussian Splatting (ICML 2025 · similarity 0.90)
- IBGS: Image-Based Gaussian Splatting (NeurIPS 2025 · similarity 0.90)
- Textured Gaussians for Enhanced 3D Scene Appearance Modeling (CVPR 2025 · similarity 0.89)
- Quantifying and Alleviating Co-Adaptation in Sparse-View 3D Gaussian Splatting (NeurIPS 2025 · similarity 0.88)
- CompactSplat: Spatially Adaptive Gaussian Distribution for Feedforward Scene Reconstruction (NeurIPS 2026 · similarity 0.88)
- ReGS: Reference-based Controllable Scene Stylization with Gaussian Splatting (NeurIPS 2024 · similarity 0.88)
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.
