Research map / Image generation / Super-resolution
SRFeat: Single Image Super-Resolution with Feature Discrimination
Seong-Jin Park, Hyeongseok Son, Sunghyun Cho, Ki-Sang Hong, Seungyong 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 feature GAN loss (feature discriminator) to SRFeatI (ablation) | SRFeatI · ILSVRC2016 val, ResNet-50 on SR images | Top-5 error (%): 11.9 -> 11.0 | Improved |
| add feature GAN loss (feature discriminator) to SRFeatI (ablation) | SRFeatI · ILSVRC2016 val, ResNet-50 on SR images | Top-1 error (%): 31.1 -> 30.9 | Improved |
| add image GAN and perceptual loss to MSE-trained generator | SRFeatM · ILSVRC2016 val, ResNet-50 on SR images | Top-5 error (%): 20.1 -> 11.9 | Improved |
| use 128 filters instead of 64 in GAN-trained generator (ablation) | SRFeatIF · ILSVRC2016 val, ResNet-50 on SR images | Top-5 error (%): 11.8 -> 11.0 | Improved |
| use 128 filters instead of 64 in GAN-trained generator (ablation) | SRFeatIF · ILSVRC2016 val, ResNet-50 on SR images | Top-1 error (%): 33.0 -> 30.9 | Improved |
| add 1x1 convolution to long-range skip connections (ablation) | SRFeatM · Set5 x4 | PSNR (dB): 32.05 -> 32.27 | Improved |
| add 1x1 convolution to long-range skip connections (ablation) | SRFeatM · Set14 x4 | PSNR (dB): 28.59 -> 28.71 | Improved |
| add 1x1 convolution to long-range skip connections (ablation) | SRFeatM · BSD100 x4 | PSNR (dB): 27.56 -> 27.64 | Improved |
| add long-range skip connections (with 1x1 conv) (ablation) | SRFeatM · Set5 x4 | PSNR (dB): 32.22 -> 32.27 | Improved |
| add long-range skip connections (with 1x1 conv) (ablation) | SRFeatM · Set14 x4 | PSNR (dB): 28.71 -> 28.71 | No clear effect |
| add long-range skip connections (with 1x1 conv) (ablation) | SRFeatM · BSD100 x4 | PSNR (dB): 27.63 -> 27.64 | Improved |
| double feature channels from 64 to 128 (ablation) | SRFeatM-64 · Set5 x4 | PSNR (dB): 32.14 -> 32.27 | Improved |
Closest papers by meaning
- SeD: Semantic-Aware Discriminator for Image Super-Resolution (CVPR 2024 · similarity 0.91)
- Exploring Semantic Feature Discrimination for Perceptual Image Super-Resolution and Opinion-Unaware No-Reference Image Quality Assessment (CVPR 2025 · similarity 0.91)
- Uncertainty-Aware GAN for Single Image Super Resolution (AAAI 2024 · similarity 0.90)
- Training Generative Image Super-Resolution Models by Wavelet-Domain Losses Enables Better Control of Artifacts (CVPR 2024 · similarity 0.90)
- GSDD: Generative Space Dataset Distillation for Image Super-resolution (AAAI 2024 · similarity 0.90)
- Noise-Started One-Step Image Super-Resolution via LR-Conditioned SplitMeanFlow and GAN Refinement (NeurIPS 2026 · similarity 0.89)
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.
