Research map / Architectures and efficiency / CNN design
JPEG Artifacts Reduction via Deep Convolutional Sparse Coding
Xueyang Fu, Zheng-Jun Zha, Feng Wu, Xinghao Ding, John Paisley
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 dilated convolutions for multi-scale features (ablation) | DCSC · LIVE1 (JPEG quality 10) | PSNR-B: 29.08 -> 29.17 | Improved |
| add dilated convolutions for multi-scale features (ablation) | DCSC · LIVE1 (JPEG quality 20) | PSNR-B: 31.39 -> 31.47 | Improved |
| add dilated convolutions for multi-scale features (ablation) | DCSC · LIVE1 (JPEG quality 30) | PSNR-B: 32.78 -> 32.81 | Improved |
| increase iterations from R = 20 to R = 40 (64 filters) (ablation) | DCSC · LIVE1 (JPEG quality 10) | PSNR: 28.46 -> 29.17 | Improved |
| increase iterations from R = 40 to R = 60 (64 filters) (ablation) | DCSC · LIVE1 (JPEG quality 10) | PSNR: 29.17 -> 29.21 | Improved |
| increase filters from 32 to 128 (R = 40) (ablation) | DCSC · LIVE1 (JPEG quality 10) | PSNR: 29.14 -> 29.19 | Improved |
| increase filters from 32 to 128 (R = 20) (ablation) | DCSC · LIVE1 (JPEG quality 10) | PSNR: 28.34 -> 28.67 | Improved |
| use MAE loss instead of MSE loss (ablation) | DCSC · LIVE1 (JPEG quality 10) | PSNR: 29.13 -> 29.17 | Improved |
| use MAE loss instead of MSE loss (ablation) | DCSC · LIVE1 (JPEG quality 20) | PSNR-B: 31.33 -> 31.47 | Improved |
| use MAE loss instead of MSE loss (ablation) | DCSC · LIVE1 (JPEG quality 30) | PSNR: 32.70 -> 32.83 | Improved |
| use DCSC instead of DnCNN (86.49% fewer parameters) | JPEG artifact reduction network · BSD500 (JPEG quality 30) | PSNR-B: 31.43 -> 32.19 | Improved |
| use DCSC instead of DnCNN | JPEG artifact reduction network · Classic5 (JPEG quality 10) | PSNR: 29.40 -> 29.25 | No clear effect |
Closest papers by meaning
- Learning Dual Priors for JPEG Compression Artifacts Removal (ICCV 2021 · similarity 0.90)
- JPEG Artifacts Removal via Contrastive Representation Learning (ECCV 2022 · similarity 0.90)
- Compression-Aware One-Step Diffusion Model for JPEG Artifact Removal (ICCV 2025 · similarity 0.89)
- Learning JPEG Compression Artifacts for Image Manipulation Detection and Localization (IJCV 2022 · similarity 0.88)
- Deep Residual Learning in the JPEG Transform Domain (ICCV 2019 · similarity 0.88)
- Frequency-Biased Synergistic Design for Image Compression and Compensation (CVPR 2025 · similarity 0.86)
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.
