Research map / Image generation / Image restoration
PUCA: Patch-Unshuffle and Channel Attention for Enhanced Self-Supervised Image Denoising
Hyemi Jang, Junsung Park, Dahuin Jung, Jaihyun Lew, Ho Bae, Sungroh Yoon
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 |
|---|---|---|---|
| U-Net level 1 to 2 (ablation) | PUCA · SIDD validation | PSNR: 36.768 -> 37.231 | Improved |
| U-Net level 2 to 3 (ablation) | PUCA · SIDD validation | PSNR: 37.231 -> 37.492 | Improved |
| U-Net level 3 to 4 (ablation) | PUCA · SIDD validation | PSNR: 37.492 -> 36.910 | Hurt |
| U-Net level 3 to 4 (ablation) | PUCA · SIDD validation | SSIM: 0.880 -> 0.878 | Hurt |
| U-Net level 1 to 3 (ablation) | PUCA · SIDD validation | SSIM: 0.875 -> 0.880 | Improved |
| pixel unshuffle instead of patch-unshuffle, no DAB (ablation) | PUCA · SIDD validation | PSNR: 37.492 -> 23.662 | Hurt |
| pixel unshuffle instead of patch-unshuffle, no DAB (ablation) | PUCA · SIDD validation | SSIM: 0.880 -> 0.328 | Hurt |
| remove downsampling (DAB, 1 level) (ablation) | PUCA · SIDD validation | PSNR: 37.492 -> 36.768 | Hurt |
| replace DAB with D-BSN block (ablation) | PUCA · SIDD validation | PSNR: 37.492 -> 37.386 | Hurt |
| replace DAB with D-BSN block (ablation) | PUCA · SIDD validation | SSIM: 0.880 -> 0.880 | No clear effect |
| PUCA vs AP-BSN | PUCA · SIDD benchmark | PSNR: 35.97 -> 37.54 | Improved |
| PUCA vs AP-BSN | PUCA · DND benchmark | PSNR: 38.09 -> 38.83 | Improved |
Closest papers by meaning
- Self-supervised Image Denoising with Downsampled Invariance Loss and Conditional Blind-Spot Network (ICCV 2023 · similarity 0.90)
- Exploring Efficient Asymmetric Blind-Spots for Self-Supervised Denoising in Real-World Scenarios (CVPR 2024 · similarity 0.90)
- Rethinking Transformer-Based Blind-Spot Network for Self-Supervised Image Denoising (AAAI 2025 · similarity 0.89)
- APR-RD: Complemental Two Steps for Self-Supervised Real Image Denoising (AAAI 2025 · similarity 0.88)
- Pseudo-Siamese Blind-spot Transformers for Self-Supervised Real-World Denoising (NeurIPS 2024 · similarity 0.88)
- Zero-Shot Noise2Mean: Gap Minimization for Efficient Denoising from a Single Noisy Image (AAAI 2025 · 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.
