Research map / Image generation / Image restoration
Multi-Scale Adaptive Network for Single Image Denoising
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use scale-specific AFeB, AMB, and AFuB together instead of the strongest reported baseline | Single-image denoising · SIDD Validation | PSNR: 39.47 -> 39.56 | Helped |
| Use scale-specific AFeB, AMB, and AFuB together instead of the strongest reported baseline | Single-image denoising · Nam | PSNR: 42.92 -> 43.52 | Helped |
| Use scale-specific AFeB, AMB, and AFuB together instead of the strongest reported baseline | Single-image denoising · DnD | PSNR: 39.63 -> 39.65 | Helped |
| Add the within-scale pair AFeB and AMB to residual blocks (ablation) | MSANet · CMcMaster, noise 30 | PSNR: 31.93 -> 31.98 | Helped |
| Add AFuB cross-scale fusion to AFeB+AMB (ablation) | MSANet · CMcMaster, noise 30 | PSNR: 31.98 -> 32.07 | Helped |
| Add AFeB and AMB together rather than using either alone (ablation) | MSANet · CMcMaster, noise 30 | PSNR: 31.94 -> 31.98 | Helped |
| Use AFeB alone on the residual-block base (ablation) | MSANet · CMcMaster, noise 30 | PSNR: 31.93 -> 31.94 | No clear effect |
| Use AMB alone on the residual-block base (ablation) | MSANet · CMcMaster, noise 30 | PSNR: 31.93 -> 31.94 | No clear effect |
| Use AFeB and AFuB without AMB (ablation) | MSANet · CMcMaster, noise 30 | PSNR: 31.93 -> 32.04 | Helped |
| Use AMB and AFuB without AFeB (ablation) | MSANet · CMcMaster, noise 30 | PSNR: 31.93 -> 32.03 | Helped |
| Replace the proposed blocks with residual blocks (ablation) | MSANet · CMcMaster, noise 30 | PSNR: 32.07 -> 31.93 | Hurt |
| Use encoder-decoder skip connections without the proposed blocks (ablation) | MSANet · CMcMaster, noise 30 | PSNR: 32.07 -> 31.70 | Hurt |
Closest papers by meaning
- Adaptive Dynamic Filtering Network for Image Denoising (AAAI 2023 · similarity 0.89)
- Universal Denoising Networks : A Novel CNN Architecture for Image Denoising (CVPR 2018 · similarity 0.87)
- LAN: Learning to Adapt Noise for Image Denoising (CVPR 2024 · similarity 0.85)
- APR-RD: Complemental Two Steps for Self-Supervised Real Image Denoising (AAAI 2025 · similarity 0.84)
- Denoising as Adaptation: Noise-Space Domain Adaptation for Image Restoration (ICLR 2025 · similarity 0.84)
- Robust Image Denoising through Adversarial Frequency Mixup (CVPR 2024 · similarity 0.84)
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.