Research map / Image generation / Image restoration
Learning Image-Adaptive Codebooks for Class-Agnostic Image Restoration
Kechun Liu, Yitong Jiang, Inchang Choi, Jinwei Gu
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 |
|---|---|---|---|
| train class-specific basis codebooks and merge them into one larger codebook (VQGAN-aux) instead of a single general codebook (ablation) | VQGAN · OST reconstruction | PSNR: 21.3557 -> 21.9219 | Improved |
| use adaptive weighted combination of basis codebooks instead of merged codebook (ablation) | VQGAN-aux · OST reconstruction | PSNR: 21.9219 -> 25.7629 | Improved |
| use adaptive weighted combination of basis codebooks instead of merged codebook (ablation) | VQGAN-aux · OST reconstruction | SSIM: 0.6030 -> 0.7705 | Improved |
| use AdaCode instead of single-codebook FeMaSR for inpainting | FeMaSR · DIV2K inpainting | LPIPS: 0.0581 -> 0.0516 | Improved |
| use AdaCode instead of Real-ESRGAN on Set5 x2 SR | Real-ESRGAN · Set5 SR x2 | PSNR: 30.032 -> 29.213 | Hurt |
| increase the number of basis codebooks (ablation) | AdaCode · OST reconstruction | PSNR and SSIM | Improved |
Closest papers by meaning
- Compressed Image Generation with Denoising Diffusion Codebook Models (ICML 2025 · similarity 0.86)
- Debiased All-in-one Image Restoration with Task Uncertainty Regularization (AAAI 2025 · similarity 0.86)
- Parameter Efficient Adaptation for Image Restoration with Heterogeneous Mixture-of-Experts (NeurIPS 2024 · similarity 0.86)
- Learning from History: Task-agnostic Model Contrastive Learning for Image Restoration (AAAI 2024 · similarity 0.86)
- Denoising as Adaptation: Noise-Space Domain Adaptation for Image Restoration (ICLR 2025 · similarity 0.86)
- Continuous Expert Assembly: Instance-Conditioned Low-Rank Residuals for All-in-One Image Restoration (NeurIPS 2026 · 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.
