Research map / 3D vision / Gaussian splatting
Bridging Diffusion Models and 3D Representations: A 3D Consistent Super-Resolution Framework
Yi-Ting Chen, Ting-Hsuan Liao, Pengsheng Guo, Alexander Schwing, Jia-Bin Huang
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-consistent diffusion SR (3DSR) instead of independent StableSR | Mip-Splatting · LLFF (x8 down, x4 up) | PSNR: 22.748 -> 24.212 | Improved |
| add 3DSR instead of StableSR | Mip-Splatting · LLFF (x8 down, x4 up) | FID: 41.129 -> 20.731 | Improved |
| add 3DSR instead of StableSR | Mip-Splatting · LLFF (x8 down, x4 up) | MEt3R: 0.531 -> 0.516 | Improved |
| add 3DSR instead of SuperGaussian (video SR) | Mip-Splatting · LLFF (x8 down, x4 up) | PSNR: 23.054 -> 24.212 | Improved |
| add 3DSR instead of DiSR-NeRF | Mip-Splatting · LLFF (x8 down, x4 up) | LPIPS: 0.310 -> 0.181 | Improved |
| add 3DSR instead of StableSR | Mip-Splatting · MipNeRF360 (x8 down, x4 up) | PSNR: 24.313 -> 26.097 | Improved |
| add 3DSR instead of StableSR | Mip-Splatting · MipNeRF360 (x8 down, x4 up) | LPIPS: 0.326 -> 0.222 | Improved |
| add 3DSR instead of SuperGaussian | Mip-Splatting · MipNeRF360 (x8 down, x4 up) | FID: 32.652 -> 22.438 | Improved |
| add 3DSR instead of SuperGaussian | Mip-Splatting · MipNeRF360 (x8 down, x4 up) | MEt3R: 0.675 -> 0.625 | Improved |
| add 3DSR instead of SuperGaussian | Mip-Splatting · LLFF (x8 down, x4 up) | NIQE: 4.553 -> 4.632 | Hurt |
| add 3DSR instead of SuperGaussian | Mip-Splatting · MipNeRF360 (x8 down, x4 up) | NIQE: 4.694 -> 5.065 | Hurt |
Closest papers by meaning
- S2Gaussian: Sparse-View Super-Resolution 3D Gaussian Splatting (CVPR 2025 · similarity 0.91)
- DiSR-NeRF: Diffusion-Guided View-Consistent Super-Resolution NeRF (CVPR 2024 · similarity 0.89)
- Sequence Matters: Harnessing Video Models in 3D Super-Resolution (AAAI 2025 · similarity 0.89)
- 3DGS-Enhancer: Enhancing Unbounded 3D Gaussian Splatting with View-consistent 2D Diffusion Priors (NeurIPS 2024 · similarity 0.89)
- Metropolis-Hastings Sampling for 3D Gaussian Reconstruction (NeurIPS 2025 · similarity 0.89)
- Wonderland: Navigating 3D Scenes from a Single Image (CVPR 2025 · 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.
