Research map / 3D vision / Gaussian splatting
Arbitrary-Scale 3D Gaussian Super-Resolution
Huimin Zeng, Yue Bai, Yun Fu
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 3D scale-aware smoothing filter (ablation) | Arbi-3DGSR · Mip-NeRF360 x8 | PSNR: 24.39 -> 24.85 | Improved |
| add 2D scale-aware Mip filter (ablation) | Arbi-3DGSR · Mip-NeRF360 x2 | PSNR: 25.53 -> 26.23 | Improved |
| use scale-dependent window instead of fixed-window 2D Mip filter (ablation) | Arbi-3DGSR · Mip-NeRF360 x4 | FID: 39.525 -> 38.526 | Improved |
| add progressive super-resolving instead of mixed random-scale training (ablation) | Arbi-3DGSR · Mip-NeRF360 x8 | PSNR: 23.91 -> 24.85 | Improved |
| add generative prior-guided optimization (ablation) | Arbi-3DGSR · Mip-NeRF360 x4 | FID: 101.618 -> 38.526 | Improved |
| add orthogonal reference refinement (ablation) | Arbi-3DGSR · Mip-NeRF360 x4 | PSNR: 25.11 -> 25.18 | Improved |
| latent distillation instead of pseudo HR supervision (ablation) | Arbi-3DGSR · Mip-NeRF360 x4 | FID: 111.574 -> 38.526 | Improved |
| latent distillation instead of SDS loss (ablation) | Arbi-3DGSR · Mip-NeRF360 x4 | PSNR: 22.91 -> 25.18 | Improved |
| cascade 3DGS with StableSR upsampler | 3DGS · Mip-NeRF360 x4 | PSNR: 20.98 -> 20.54 | Mixed |
| cascade 3DGS with bicubic upsampling | 3DGS · Mip-NeRF360 x4 | PSNR: 20.98 -> 25.09 | Improved |
| generative prior training adds training cost | Arbi-3DGSR vs 3DGS · efficiency, A6000 | training minutes: 10 -> 57 | 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.
- Mip-Splatting — Mip-Splatting: Alias-free 3D Gaussian Splatting (CVPR 2024) · better on 6 of 6 shared results
- Analytic-Splatting — Analytic-Splatting: Anti-Aliased 3D Gaussian Splatting via Analytic Integration (ECCV 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
- Multi-Scale 3D Gaussian Splatting for Anti-Aliased Rendering (CVPR 2024 · similarity 0.91)
- FlashGS: Efficient 3D Gaussian Splatting for Large-scale and High-resolution Rendering (CVPR 2025 · similarity 0.90)
- Steepest Descent Density Control for Compact 3D Gaussian Splatting (CVPR 2025 · similarity 0.90)
- IBGS: Image-Based Gaussian Splatting (NeurIPS 2025 · similarity 0.90)
- DashGaussian: Optimizing 3D Gaussian Splatting in 200 Seconds (CVPR 2025 · similarity 0.89)
- GaussianPro: 3D Gaussian Splatting with Progressive Propagation (ICML 2024 · 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.
