Research map / Image generation / Image restoration
TPGDiff : Hierarchical Triple-Prior Guided Diffusion for Image Restoration
Yanjie Tu, Qingsen Yan, Axi Niu, Jiacong Tang
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 semantic prior on top of degradation prior (ablation) | TPGDiff · Rain200L+Snow100K-L avg (ablation) | PSNR: 31.93 -> 32.61 | Improved |
| add degradation prior to baseline (ablation) | TPGDiff · Rain200L+Snow100K-L avg (ablation) | PSNR: 31.63 -> 31.93 | Improved |
| add structural prior (ablation) | TPGDiff · Rain200L+Snow100K-L avg (ablation) | LPIPS: 0.049 -> 0.045 | Improved |
| add structural prior (ablation) | TPGDiff · Rain200L+Snow100K-L avg (ablation) | PSNR: 32.61 -> 32.63 | Improved |
| semantic prior deep, structural prior shallow (vs swapped) (ablation) | TPGDiff · Rain200L+Snow100K-L avg (ablation) | PSNR: 32.18 -> 32.63 | Improved |
| inject both priors at all layers (vs aligned positions) (ablation) | TPGDiff · Rain200L+Snow100K-L avg (ablation) | PSNR: 32.63 -> 31.51 | Hurt |
| add depth cue to structural prior (ablation) | TPGDiff · Rain200L+LOL-v2 | PSNR: 29.00 -> 29.46 | Improved |
| add segmentation cue to structural prior (ablation) | TPGDiff · Rain200L+LOL-v2 | PSNR: 29.22 -> 29.46 | Improved |
| add DoG cue to structural prior (ablation) | TPGDiff · Rain200L+LOL-v2 | PSNR: 28.94 -> 29.46 | Improved |
| TPGDiff vs best baseline on 5-task average | TPGDiff · All-in-one 5-task | PSNR: 30.11 -> 30.60 | Improved |
| TPGDiff vs VLU-Net on denoising | TPGDiff · All-in-one 5-task denoising | PSNR: 31.43 -> 30.58 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- FoundIR-v2 — FoundIR-v2: Optimizing Pre-Training Data Mixtures for Image Restoration Foundation Model (CVPR 2026) · 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
- GenDeg: Diffusion-based Degradation Synthesis for Generalizable All-In-One Image Restoration (CVPR 2025 · similarity 0.89)
- Learning Diffusion Texture Priors for Image Restoration (CVPR 2024 · similarity 0.88)
- Visual-Instructed Degradation Diffusion for All-in-One Image Restoration (CVPR 2025 · similarity 0.88)
- DGSolver: Diffusion Generalist Solver with Universal Posterior Sampling for Image Restoration (NeurIPS 2025 · similarity 0.88)
- IRBridge: Solving Image Restoration Bridge with Pre-trained Generative Diffusion Models (ICML 2025 · similarity 0.88)
- RAP-SR: RestorAtion Prior Enhancement in Diffusion Models for Realistic Image Super-Resolution (AAAI 2025 · similarity 0.88)
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.
