Research map / 3D vision / Gaussian splatting
Pano-GS: Perception-Aware Gaussian Optimization with Gradient Consistency and Multi-Criteria Densification for High-Quality Rendering
Yang Deng, Zhanke Wang, Jiahao Wu, Jie Liang, Jingui Ma, Yang Hu, Ronggang Wang
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 gradient consistency-constrained loss (ablation) | Scaffold-GS · Tanks&Temples | PSNR: 24.05 -> 24.45 | Improved |
| add gradient consistency-constrained loss (ablation) | Scaffold-GS · Tanks&Temples | LPIPS: 0.173 -> 0.151 | Improved |
| add multi-criteria densification only (ablation) | Scaffold-GS · Tanks&Temples | LPIPS: 0.173 -> 0.146 | Improved |
| add stochastic perturbation exploration only (ablation) | Scaffold-GS · Tanks&Temples | PSNR: 24.05 -> 24.20 | Improved |
| add MDS and SPE on top of GCL (ablation) | Pano-GS · Tanks&Temples | PSNR: 24.45 -> 24.56 | Improved |
| add SPE to GCL+MDS (ablation) | Pano-GS · Tanks&Temples | LPIPS: 0.137 -> 0.136 | No clear effect |
| Pano-GS vs Scaffold-GS | Scaffold-GS · Mip-NeRF 360 | PSNR: 27.59 -> 28.08 | Improved |
| Pano-GS vs Revised-GS/Pixel-GS SSIM | 3DGS baselines · Mip-NeRF 360 | SSIM: 0.823 -> 0.818 | Hurt |
| Pano-GS vs Pixel-GS LPIPS | Pixel-GS · Mip-NeRF 360 | LPIPS: 0.194 -> 0.194 | No clear effect |
| Pano-GS vs Pixel-GS model size | Pixel-GS · Mip-NeRF 360 | model size: 1.24 GB -> 420 MB | Improved |
| Pano-GS vs Scaffold-GS training time and size | Scaffold-GS · Mip-NeRF 360 | training time (min): 40 m -> 70 m | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- Scaffold-GS — Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering (CVPR 2024) · better on 5 of 8 shared results
- Mip-Splatting — Mip-Splatting: Alias-free 3D Gaussian Splatting (CVPR 2024) · 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
- Perceptual-GS: Scene-adaptive Perceptual Densification for Gaussian Splatting (ICML 2025 · similarity 0.93)
- F⁴Splat: Feed-Forward Predictive Densification for Feed-Forward 3D Gaussian Splatting (ECCV 2026 · similarity 0.92)
- Generative Sparse-View Gaussian Splatting (CVPR 2025 · similarity 0.90)
- PUP 3D-GS: Principled Uncertainty Pruning for 3D Gaussian Splatting (CVPR 2025 · similarity 0.90)
- Speedy-Splat: Fast 3D Gaussian Splatting with Sparse Pixels and Sparse Primitives (CVPR 2025 · similarity 0.90)
- Generative Densification: Learning to Densify Gaussians for High-Fidelity Generalizable 3D Reconstruction (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.
