Research map / 3D vision / Gaussian splatting
GSFixer: Improving 3D Gaussian Splatting with Reference-Guided Video Diffusion Priors
Xingyilang Yin, Qi Zhang, Jiahao Chang, Ying Feng, Qingnan Fan, Xi Yang, Chi-Man Pun, Huaqi Zhang, Xiaodong Cun
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 VGGT 3D geometric tokens (ablation) | GSFixer · DL3DV-Res | PSNR: 16.36 -> 16.72 | Improved |
| add DINOv2 2D semantic tokens (ablation) | GSFixer · DL3DV-Res | PSNR: 16.48 -> 16.72 | Improved |
| add 3D tokens (ablation) | GSFixer · DL3DV-Res | LPIPS: 0.414 -> 0.399 | Improved |
| add 2D tokens (ablation) | GSFixer · DL3DV-Res | LPIPS: 0.409 -> 0.399 | Improved |
| use reference-guided trajectory instead of interpolation trajectory (ablation) | GSFixer · Mip-NeRF 360 (3-view) | PSNR: 14.50 -> 15.61 | Improved |
| use reference-guided trajectory instead of ellipse trajectory (ablation) | GSFixer · Mip-NeRF 360 (3-view) | PSNR: 15.46 -> 15.61 | Improved |
| use reference-guided trajectory instead of ellipse trajectory (ablation) | GSFixer · Mip-NeRF 360 (3-view) | LPIPS: 0.563 -> 0.559 | Improved |
| GSFixer restoration instead of GenFusion | video restoration · DL3DV-Res | PSNR: 14.56 -> 16.72 | Improved |
| apply GSFixer to 3DGS with 3 input views | 3DGS · DL3DV-Benchmark (3-view) | PSNR: 13.72 -> 16.21 | Improved |
| GSFixer vs Difix3D+ with 9 views, LPIPS | GSFixer · DL3DV-Benchmark (9-view) | LPIPS: 0.259 -> 0.307 | Hurt |
| GSFixer vs ReconFusion (NeRF-based generative) | GSFixer · Mip-NeRF 360 (3-view) | PSNR: 15.50 -> 15.61 | Improved |
| Difix3D+ and GenFusion restoration versus unrestored frames on consistency | Difix3D+, GenFusion · DL3DV-Res | I2V_SC: 0.9382 -> 0.9288 | Hurt |
Later papers that compared with this method
1 later accepted paper reports GSFixer as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- DualDiff3D: Dual Structure-Appearance Diffusion Priors for Reliability-Enhanced 3D Gaussian Splatting (ECCV 2026 · better on 1 of 1 shared result)
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.
- GenFusion — GenFusion: Closing the Loop between Reconstruction and Generation via Videos (CVPR 2025) · better on 6 of 6 shared results
- ReconFusion — ReconFusion: 3D Reconstruction with Diffusion Priors (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
- Taming Video Diffusion Prior with Scene-Grounding Guidance for 3D Gaussian Splatting from Sparse Inputs (CVPR 2025 · similarity 0.92)
- 3DGS-Enhancer: Enhancing Unbounded 3D Gaussian Splatting with View-consistent 2D Diffusion Priors (NeurIPS 2024 · similarity 0.92)
- Generative Sparse-View Gaussian Splatting (CVPR 2025 · similarity 0.91)
- Learning Efficient Fuse-and-Refine for Feed-Forward 3D Gaussian Splatting (NeurIPS 2025 · similarity 0.90)
- TranSplat: Generalizable 3D Gaussian Splatting from Sparse Multi-View Images with Transformers (AAAI 2025 · similarity 0.90)
- GaussianSpa: An "Optimizing-Sparsifying" Simplification Framework for Compact and High-Quality 3D Gaussian Splatting (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.
