Research map / 3D vision / Gaussian splatting
RI3D: Few-Shot Gaussian Splatting With Repair and Inpainting Diffusion Priors
Avinash Paliwal, Xilong Zhou, Wei Ye, Jinhui Xiong, Rakesh Ranjan, Nima Khademi Kalantari
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 depth enhancement combining DUSt3R and monocular depth (ablation) | RI3D · Mip-NeRF 360 (3-view) | PSNR: 15.61 -> 15.74 | Improved |
| add depth enhancement combining DUSt3R and monocular depth (ablation) | RI3D · Mip-NeRF 360 (3-view) | LPIPS: 0.513 -> 0.505 | Improved |
| use two-stage optimization instead of single stage with repair model only (ablation) | RI3D · Mip-NeRF 360 (3-view) | PSNR: 14.92 -> 15.74 | Improved |
| use two-stage optimization instead of single stage with repair model only (ablation) | RI3D · Mip-NeRF 360 (3-view) | LPIPS: 0.527 -> 0.505 | Improved |
| add fine-tuning of the inpainting model on input images (ablation) | RI3D · Mip-NeRF 360 (3-view) | PSNR: 15.64 -> 15.74 | Improved |
| add fine-tuning of the inpainting model on input images (ablation) | RI3D · Mip-NeRF 360 (3-view) | LPIPS: 0.508 -> 0.505 | Improved |
| RI3D versus CAT3D on perceptual quality | RI3D · Mip-NeRF 360 (3-view) | LPIPS: 0.515 -> 0.505 | Improved |
| RI3D versus CAT3D on pixel metrics | RI3D · Mip-NeRF 360 (3-view) | PSNR: 16.62 -> 15.74 | Hurt |
| RI3D versus FSGS on perceptual quality | RI3D · Mip-NeRF 360 (3-view) | LPIPS: 0.578 -> 0.505 | Improved |
| RI3D versus CAT3D on CO3D | RI3D · CO3D (3-view) | LPIPS: 0.351 -> 0.385 | Hurt |
| RI3D versus ReconFusion on CO3D at 9 views | RI3D · CO3D (9-view) | LPIPS: 0.318 -> 0.277 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.
- CAT3D — CAT3D: Create Anything in 3D with Multi-View Diffusion Models (NeurIPS 2024) · better on 3 of 10 shared results
- ReconFusion — ReconFusion: 3D Reconstruction with Diffusion Priors (CVPR 2024) · better on 3 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
- Wonderland: Navigating 3D Scenes from a Single Image (CVPR 2025 · similarity 0.90)
- Taming Video Diffusion Prior with Scene-Grounding Guidance for 3D Gaussian Splatting from Sparse Inputs (CVPR 2025 · similarity 0.90)
- Generative Sparse-View Gaussian Splatting (CVPR 2025 · similarity 0.90)
- GaussianSpa: An "Optimizing-Sparsifying" Simplification Framework for Compact and High-Quality 3D Gaussian Splatting (CVPR 2025 · similarity 0.90)
- RestorGS: Depth-aware Gaussian Splatting for Efficient 3D Scene Restoration (CVPR 2025 · similarity 0.90)
- ReorgGS: Equivalent Distribution Reorganization for 3D Gaussian Splatting (NeurIPS 2026 · 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.
