Research map / Label-efficient and robust learning / Test-time adaptation
Degradation-Consistent Test-Time Adaptation for All-in-One Image Restoration
Ni Tang, Shenghao Nie, Xiaotong Luo, Yuan Xie, Yanyun Qu
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 DCTTA to PromptIR | PromptIR · Rain100H (three-task setting) | PSNR: 15.64 -> 20.21 | Improved |
| add DCTTA to AirNet | AirNet · DenseHaze (three-task setting) | PSNR: 10.90 -> 12.49 | Improved |
| add DCTTA to PromptIR | PromptIR · Kodak24 (Poisson noise) | PSNR: 25.41 -> 25.78 | Improved |
| add DCTTA to PromptIR | PromptIR · O-HAZY | PSNR: 16.70 -> 16.78 | No clear effect |
| add DCTTA to AirNet on five-task setting | AirNet · Five-task average | PSNR: 17.75 -> 19.96 | Improved |
| add DCTTA to DFPIR on five-task setting | DFPIR · Five-task average | PSNR: 22.61 -> 23.61 | Improved |
| add DCTTA to PromptIR on mixed rain streak and raindrop | PromptIR · Rainstreak & Raindrop mixed | PSNR: 18.06 -> 18.27 | Improved |
| add inference-time geometric augmentation only (no adaptation) | PromptIR · Rain100H (three-task setting) | PSNR: 15.64 -> 15.72 | No clear effect |
| add test-time important parameter selection (TIPS) (ablation) | DCTTA (PromptIR) · Rain100H | PSNR: 14.24 -> 20.21 | Improved |
| add data augmentation ensemble for pseudo-labels (ablation) | DCTTA (PromptIR) · Rain100H | PSNR: 19.57 -> 20.21 | Improved |
| add EMA teacher update (ablation) | DCTTA (PromptIR) · Rain100H | PSNR: 19.87 -> 20.21 | Improved |
| use RDDM diffusion degradation generator instead of CNN generator (ablation) | DCTTA (PromptIR) · Rain100H | PSNR: 17.43 -> 20.21 | Improved |
Closest papers by meaning
- Test-Time Degradation Adaptation for Open-Set Image Restoration (ICML 2024 · similarity 0.91)
- Diffusion Once and Done: Degradation-Aware LoRA for All-in-One Image Restoration (AAAI 2026 · similarity 0.90)
- A Survey on All-in-One Image Restoration: Taxonomy, Evaluation and Future Trends (TPAMI 2025 · similarity 0.90)
- Continuous Expert Assembly: Instance-Conditioned Low-Rank Residuals for All-in-One Image Restoration (NeurIPS 2026 · similarity 0.88)
- GenDeg: Diffusion-based Degradation Synthesis for Generalizable All-In-One Image Restoration (CVPR 2025 · similarity 0.88)
- Learning Where and What to Restore for Composite Image Restoration (NeurIPS 2026 · 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.
