Research map / Image generation / Super-resolution
Fast Image Restoration With Multi-Bin Trainable Linear Units
Shuhang Gu, Wen Li, Luc Van Gool, Radu Timofte
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 |
|---|---|---|---|
| replace ReLU with MTLU (ablation) | ESPCN · Set5 x4 | PSNR (dB): 30.66 -> 30.82 | Improved |
| replace ReLU with MTLU (ablation) | FSRCNN · Set5 x4 | PSNR (dB): 30.73 -> 30.96 | Improved |
| replace PReLU with MTLU (ablation) | SRResNet · Set5 x4 | PSNR (dB): 32.06 -> 32.13 | Improved |
| replace ReLU with MTLU (ablation) | SRResNet · Set14 x4 | PSNR (dB): 28.49 -> 28.54 | Improved |
| replace PReLU with MTLU (ablation) | FSRnet7 · Set5 x4 | PSNR (dB): 31.43 -> 31.52 | Improved |
| replace PReLU with MTLU (ablation) | FDnet10 · BSD68 sigma=50 | PSNR (dB): 26.14 -> 26.24 | Improved |
| replace PLF40 with MTLU40 (ablation) | FSRnet7 · Set5 x4 | PSNR (dB): 31.39 -> 31.52 | Improved |
| replace PLF40 with MTLU40 (ablation) | FDnet10 · BSD68 sigma=50 | PSNR (dB): 26.06 -> 26.24 | Improved |
| replace APL10 with MTLU40 (ablation) | FSRnet7 · Set5 x4 | PSNR (dB): 31.35 -> 31.52 | Improved |
| replace APL10 with MTLU40 (runtime) (ablation) | FSRnet7 · 512x512 image runtime (ms) | runtime (ms): 16.0 -> 4.0 | Improved |
| use bin-width 0.5 instead of 0.05 (ablation) | FSRnet7 MTLU · Set5 x4 | PSNR (dB): 31.52 -> 31.43 | Hurt |
| increase number of bins from 20 to 80 (ablation) | FSRnet7 MTLU · Set5 x4 | PSNR (dB): 31.50 -> 31.54 | No clear effect |
Closest papers by meaning
- CLEARER: Multi-Scale Neural Architecture Search for Image Restoration (NeurIPS 2020 · similarity 0.89)
- xUnit: Learning a Spatial Activation Function for Efficient Image Restoration (CVPR 2018 · similarity 0.89)
- Functional Neural Networks for Parametric Image Restoration Problems (NeurIPS 2021 · similarity 0.89)
- End-to-End Learning for Joint Image Demosaicing, Denoising and Super-Resolution (CVPR 2021 · similarity 0.88)
- Denoising Prior Driven Deep Neural Network for Image Restoration (TPAMI 2018 · similarity 0.88)
- A Restoration Network as an Implicit Prior (ICLR 2024 · similarity 0.87)
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.
