Research map / Image generation / Super-resolution
Toward DNN of LUTs: Learning Efficient Image Restoration With Multiple Look-Up Tables
Jiacheng Li, Chang Chen, Zhen Cheng, 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 |
|---|---|---|---|
| add complementary D pattern to S (parallel LUTs) (ablation) | MuLUT x4 SR · Manga109 x4 | PSNR: 26.80 -> 27.38 | Improved |
| use complementary patterns instead of repeating S pattern (ablation) | MuLUT x4 SR · Manga109 x4 | PSNR: 26.96 -> 27.38 | Improved |
| replace T pattern by Y pattern (ablation) | MuLUT-SD based · Manga109 x4 | PSNR: 27.50 -> 27.52 | Improved |
| add E, H, O patterns to SDY (ablation) | MuLUT x4 SR · Manga109 x4 | PSNR: 27.52 -> 27.53 | No clear effect |
| add LUT re-indexing to cascaded stages (ablation) | MuLUT-S-X2 · Manga109 x4 | PSNR: 27.02 -> 27.39 | Improved |
| cascade more stages (X2 to X4) (ablation) | MuLUT-S · Manga109 x4 | PSNR: 27.39 -> 27.66 | Improved |
| add hierarchical indexing to SDY (ablation) | MuLUT-SDY · Manga109 x4 | PSNR: 27.52 -> 27.90 | Improved |
| add channel indexing (ablation) | MuLUT-SDY-X2 demosaicing · Kodak | cPSNR: 37.11 -> 37.54 | Improved |
| add channel indexing (ablation) | MuLUT-SDYEHO-X2 color denoising · Kodak24 sigma 50 | cPSNR: 25.80 -> 26.49 | Improved |
| add LUT-aware finetuning (ablation) | SR-LUT (3bit) · Manga109 x4 | PSNR: 26.76 -> 26.85 | Improved |
| add LUT-aware finetuning (ablation) | MuLUT-SDY-X2 · Manga109 x4 | PSNR: 27.83 -> 27.90 | Improved |
| increase filters of SR-LUT network (nf 64 to 256) (ablation) | SR-LUT · Manga109 x4 | PSNR: 26.80 -> 26.89 | No clear effect |
Closest papers by meaning
- TinyLUT: Tiny Look-Up Table for Efficient Image Restoration at the Edge (NeurIPS 2024 · similarity 0.91)
- MuLUT: Cooperating Multiple Look-Up Tables for Efficient Image Super-Resolution (ECCV 2022 · similarity 0.91)
- Efficient Look-Up Table from Expanded Convolutional Network for Accelerating Image Super-resolution (AAAI 2024 · similarity 0.87)
- NILUT: Conditional Neural Implicit 3D Lookup Tables for Image Enhancement (AAAI 2024 · similarity 0.87)
- Omni-Kernel Network for Image Restoration (AAAI 2024 · similarity 0.87)
- Look-Up Table Compression for Efficient Image Restoration (CVPR 2024 · 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.
