Research map / Image generation / Image restoration
Compression Artifacts Removal for VVC with Frequency Domain Mixture of Experts Network
Qijun Wang, Kang Wang, Jun Wang
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 Frequency Domain MoE (frequency experts) to the SW-MSA baseline (ablation) | ARMoE · VVC-CAR Kodak24 (QP=37) | PSNR: 32.75 -> 32.87 | Improved |
| add Frequency Domain MoE to the SW-MSA baseline (ablation) | ARMoE · VVC-CAR McMaster (QP=37) | PSNR: 33.59 -> 33.81 | Improved |
| add Frequency-Aware Factors (FAF) (ablation) | ARMoE · VVC-CAR Kodak24 (QP=37) | PSNR: 32.67 -> 32.87 | Improved |
| add Frequency-Aware Factors (FAF) (ablation) | ARMoE · VVC-CAR McMaster (QP=37) | PSNR: 33.51 -> 33.81 | Improved |
| use L1 loss instead of Charbonnier loss (ablation) | ARMoE · VVC-CAR Kodak24 (QP=37) | PSNR: 32.83 -> 32.87 | Improved |
| use L1 loss instead of Charbonnier loss (ablation) | ARMoE · VVC-CAR McMaster (QP=37) | PSNR: 33.77 -> 33.81 | Improved |
| use ARMoE instead of RGT (best baseline) | image restoration backbone · VVC-CAR Kodak24 (QP=37) | PSNR: 32.84 -> 32.87 | Improved |
| use ARMoE instead of best baseline | image restoration backbone · BD-rate Class B (QP=37) | BD-rate: -11.47 -> -12.55 | Improved |
| use ARMoE (lightweight) instead of MambaIR | lightweight SR x2 · Set5 | PSNR: 38.13 -> 38.23 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- MambaIR — MambaIR: A Simple Baseline for Image Restoration with State-Space Model (ECCV 2024) · better on 5 of 5 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- One-To-Many Network for Visually Pleasing Compression Artifacts Reduction (CVPR 2017 · similarity 0.86)
- Compression-Aware One-Step Diffusion Model for JPEG Artifact Removal (ICCV 2025 · similarity 0.85)
- Frequency-Biased Synergistic Design for Image Compression and Compensation (CVPR 2025 · similarity 0.82)
- Blind Bitstream-corrupted Video Recovery via Metadata-guided Diffusion Model (CVPR 2025 · similarity 0.82)
- Visual Redundancy Removal for Composite Images: A Benchmark Dataset and a Multi-Visual-Effects Driven Incremental Method (AAAI 2024 · similarity 0.82)
- Motion Artifact Removal in Pixel-Frequency Domain via Alternate Masks and Diffusion Model (AAAI 2025 · similarity 0.81)
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.
