Research map / Image generation / Super-resolution
IM-LUT: Interpolation Mixing Look-Up Tables for Image Super-Resolution
Sejin Park, Sangmin Lee, Kyong Hwan Jin, Seung-Won Jung
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 refiner (ablation) | IM-Net · Set5 x2 | PSNR: 35.81 -> 36.26 | Improved |
| add scale modulator (ablation) | IM-Net · Set5 x2 | PSNR: 35.81 -> 36.04 | Improved |
| add guidance loss (ablation) | IM-Net · Set5 x2 | PSNR: 35.81 -> 35.95 | Improved |
| add all three: guidance loss, scale modulator, refiner (ablation) | IM-Net · Set5 x2 | PSNR: 35.81 -> 36.48 | Improved |
| add scale modulator to guide+refiner (ablation) | IM-Net · Set5 x2 | PSNR: 36.40 -> 36.48 | Improved |
| add guidance loss to scale modulator+refiner (ablation) | IM-Net · Set5 x4 | PSNR: 30.40 -> 30.46 | Improved |
| add refiner to guide+scale modulator (ablation) | IM-Net · Set5 x4 | PSNR: 30.03 -> 30.46 | Improved |
| add zlanczos interpolation to NLC (NLCZ) | IM-LUT · Set5 x2 | PSNR: 36.20 -> 36.35 | Improved |
| add bicubic to NL (NLC) | IM-LUT · Set5 x2 | PSNR: 35.83 -> 36.20 | Improved |
| coarser LUT sampling interval 2^0 to 2^5 (ablation) | IM-LUT NLC · Set5 x2 | PSNR: 36.48 -> 36.20 | Mixed |
| coarser LUT sampling interval 2^5 to 2^6 (ablation) | IM-LUT NLC · Set5 x2 | PSNR: 36.20 -> 35.58 | Hurt |
| use IM-LUT NLC instead of LeRF-G | IM-LUT · Set5 x2 | CPU runtime: 5.51s -> 2.73s | Improved |
Closest papers by meaning
- Practical Single-Image Super-Resolution Using Look-Up Table (CVPR 2021 · similarity 0.89)
- Learning Series-Parallel Lookup Tables for Efficient Image Super-Resolution (ECCV 2022 · similarity 0.87)
- Efficient Look-Up Table from Expanded Convolutional Network for Accelerating Image Super-resolution (AAAI 2024 · similarity 0.86)
- TSD-SR: One-Step Diffusion with Target Score Distillation for Real-World Image Super-Resolution (CVPR 2025 · similarity 0.85)
- SinSR: Diffusion-Based Image Super-Resolution in a Single Step (CVPR 2024 · similarity 0.85)
- NSARM: Next-Scale Autoregressive Modeling for Robust Real-World Image Super-Resolution (NeurIPS 2026 · similarity 0.85)
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.
