Research map / Image generation / Image restoration
Unfolding Taylor's Approximations for Image Restoration
man zhou, Xueyang Fu, Zeyu Xiao, Gang Yang, Aiping Liu, Zhiwei Xiong
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 |
|---|---|---|---|
| integrate 3-order Taylor framework | DCM · Rain100L | PSNR (dB): 37.15 -> 37.31 | Improved |
| integrate 3-order Taylor framework | PReNet · Rain100L | PSNR (dB): 32.44 -> 34.44 | Improved |
| integrate 3-order Taylor framework | PReNet · Rain100H | PSNR (dB): 26.77 -> 26.78 | No clear effect |
| integrate 3-order Taylor framework | DDN · Rain100L | PSNR (dB): 34.85 -> 35.16 | Improved |
| integrate 3-order Taylor framework | MPRnet · Rain100H | PSNR (dB): 30.44 -> 30.52 | Improved |
| integrate 3-order Taylor framework | DCM · GoPro | PSNR (dB): 30.25 -> 30.39 | Improved |
| integrate 3-order Taylor framework | DCM · RealBlur-J | PSNR (dB): 35.55 -> 35.91 | Improved |
| integrate 3-order Taylor framework | MSCNN · GoPro | PSNR (dB): 29.08 -> 29.19 | Improved |
| integrate 3-order Taylor framework | RDN · GoPro | PSNR (dB): 29.20 -> 29.31 | Improved |
| increase Taylor order from 3 to 4 (ablation) | DCM · Rain100L | PSNR (dB): 37.31 -> 37.22 | Hurt |
| increase Taylor order from 0 to 3 (ablation) | DCM · Rain100L | PSNR (dB): 37.15 -> 37.31 | Improved |
| increase Taylor order from 3 to 6 (ablation) | DCM · GoPro | PSNR (dB): 30.39 -> 30.36 | Hurt |
Closest papers by meaning
- Learning Enriched Features for Fast Image Restoration and Enhancement (TPAMI 2022 · similarity 0.90)
- MB-TaylorFormer V2: Improved Multi-Branch Linear Transformer Expanded by Taylor Formula for Image Restoration (TPAMI 2025 · similarity 0.89)
- ReFIR: Grounding Large Restoration Models with Retrieval Augmentation (NeurIPS 2024 · similarity 0.88)
- Omni-Kernel Network for Image Restoration (AAAI 2024 · similarity 0.87)
- A Restoration Network as an Implicit Prior (ICLR 2024 · similarity 0.87)
- UP-Restorer: When Unrolling Meets Prompts for Unified Image Restoration (AAAI 2025 · similarity 0.86)
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.
