Research map / Image generation / Image restoration
Exploiting Diffusion Prior for Task-driven Image Restoration
Jaeha Kim, Junghun Oh, Kyoung Mu Lee
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 HLF loss (features of both task networks) (ablation) | EDTR-1 step · Classification Mixture-B | accuracy: 67.8 -> 68.8 | Improved |
| add feature-matching (FM) loss (ablation) | EDTR-1 step · Classification Mixture-B | accuracy: 67.6 -> 68.8 | Hurt |
| add partial diffusion (ablation) | EDTR-1 step · Classification Mixture-B | accuracy: 63.5 -> 66.6 | Improved |
| add pre-restoration (SwinIR) before diffusion (ablation) | EDTR-1 step · Classification Mixture-B | accuracy: 66.6 -> 68.8 | Improved |
| add HLF loss to SD at 50 steps (ablation) | EDTR · Classification Mixture-B | accuracy: 64.3 -> 62.9 | Hurt |
| use 1 denoising step instead of 50 (ablation) | EDTR with HLF loss · Classification Mixture-B | accuracy: 62.9 -> 63.5 | Improved |
| use Stable Diffusion prior (ablation) | EDTR-1 step · Classification Mixture-B | accuracy: 64.2 -> 68.8 | Improved |
| increase denoising steps from 4 to 50 (ablation) | EDTR · Classification Mixture-B | accuracy: 68.4 -> 66.8 | Hurt |
| increase denoising steps from 1 to 4 (ablation) | EDTR · Semantic segmentation | mIoU: 60.4 -> 62.9 | Improved |
| add trainable VAE decoder (ablation) | EDTR-1 step · Classification Mixture-B | accuracy: 67.7 -> 68.8 | Improved |
| add wavelet color correction (ablation) | EDTR-1 step · Classification Mixture-B | accuracy: 68.4 -> 68.8 | Improved |
| use SwinIR instead of EDSR for pre-restoration (ablation) | EDTR-1 step · Classification Mixture-B | accuracy: 66.8 -> 68.8 | Improved |
Closest papers by meaning
- Learning Diffusion Texture Priors for Image Restoration (CVPR 2024 · similarity 0.90)
- Denoising Task Routing for Diffusion Models (ICLR 2024 · similarity 0.89)
- Diffusion Priors for Variational Likelihood Estimation and Image Denoising (NeurIPS 2024 · similarity 0.89)
- DiffusionMTL: Learning Multi-Task Denoising Diffusion Model from Partially Annotated Data (CVPR 2024 · similarity 0.88)
- Visual-Instructed Degradation Diffusion for All-in-One Image Restoration (CVPR 2025 · similarity 0.88)
- What Matters When Repurposing Diffusion Models for General Dense Perception Tasks? (ICLR 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.
