Research map / Image generation / Image restoration
Multi-Decoding Deraining Network and Quasi-Sparsity Based Training
Check 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 |
|---|---|---|---|
| add quasi-sparsity loss LQ to content loss (ablation) | QSMD · Test-I | PSNR: 29.94 -> 31.70 | Helped |
| add quasi-sparsity loss LQ to content loss (ablation) | QSMD · Test-II | PSNR: 34.15 -> 34.50 | Helped |
| add low-value prior loss LD after content and quasi-sparsity losses (ablation) | QSMD · Test-I | PSNR: 31.70 -> 32.03 | Helped |
| add low-value prior loss LD after content and quasi-sparsity losses (ablation) | QSMD · Test-II | PSNR: 34.50 -> 34.85 | Helped |
| add auxiliary decoder loss LA after content, quasi-sparsity, and low-value losses (ablation) | QSMD · Test-I | PSNR: 32.03 -> 33.15 | Helped |
| add auxiliary decoder loss LA after content, quasi-sparsity, and low-value losses (ablation) | QSMD · Test-II | PSNR: 34.85 -> 35.66 | Helped |
| add information sharing between feature spaces (ablation) | QSMD · Test-I | PSNR: 31.91 -> 33.15 | Helped |
| add information sharing between feature spaces (ablation) | QSMD · Test-II | PSNR: 34.51 -> 35.66 | Helped |
Closest papers by meaning
- Unsupervised Deraining: Where Contrastive Learning Meets Self-Similarity (CVPR 2022 · similarity 0.92)
- Harnessing Joint Rain-/Detail-aware Representations to Eliminate Intricate Rains (ICLR 2024 · similarity 0.90)
- Rethinking Multi-Scale Representations in Deep Deraining Transformer (AAAI 2024 · similarity 0.90)
- Bidirectional Multi-Scale Implicit Neural Representations for Image Deraining (CVPR 2024 · similarity 0.89)
- Channel Consistency Prior and Self-Reconstruction Strategy Based Unsupervised Image Deraining (CVPR 2025 · similarity 0.88)
- Boosting Image De-Raining via Central-Surrounding Synergistic Convolution (AAAI 2025 · similarity 0.88)
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.