Research map / Image generation / Image restoration
RIDCP: Revitalizing Real Image Dehazing via High-Quality Codebook Priors
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 RIDCP instead of PSD | Real image dehazing · RTTS | FADE: 0.920 -> 0.944 | Hurt |
| Use RIDCP instead of PSD | Real image dehazing · RTTS | BRISQUE: 25.23}9 -> 18.782 | Helped |
| Use RIDCP instead of PSD | Real image dehazing · RTTS | NIMA: 4.3459 -> 4.4267 | Helped |
| Use RIDCP instead of DAD | Real image dehazing · RTTS | US: 0.143 -> 0.556 | Helped |
| Add the full NFA (deformable warping plus normalized addition) (ablation) | RIDCP · Qualitative NFA ablation | visual dehazing quality | Helped |
| Remove all feature fusion (ablation) | RIDCP · Qualitative NFA ablation | visual dehazing quality | Hurt |
| Replace NFA with direct addition (ablation) | RIDCP · Qualitative NFA ablation | visual dehazing quality | Hurt |
| Remove warping while retaining normalized addition (ablation) | RIDCP · Qualitative NFA ablation | visual artifact severity | Hurt |
| Use the proposed phenomenological degradation pipeline instead of OTS or Haze4K training data (ablation) | RIDCP · Real image dehazing | haze removal | Helped |
| Train Dehamer with the proposed synthetic data instead of OTS (ablation) | Dehamer · Real image dehazing | haze residue | Helped |
| Train MSBDN with the proposed synthetic data instead of OTS (ablation) | MSBDN · Real image dehazing | haze residue | Helped |
| Use HQPs from the high-quality codebook (ablation) | RIDCP · Qualitative HQPs ablation | brightness | Helped |
Closest papers by meaning
- PromptHaze: Prompting Real-world Dehazing via Depth Anything Model (AAAI 2025 · similarity 0.89)
- Iterative Predictor-Critic Code Decoding for Real-World Image Dehazing (CVPR 2025 · similarity 0.89)
- Learning Hazing to Dehazing: Towards Realistic Haze Generation for Real-World Image Dehazing (CVPR 2025 · similarity 0.89)
- Exploiting Diffusion Prior for Real-World Image Dehazing with Unpaired Training (AAAI 2025 · similarity 0.89)
- Real-world Image Dehazing with Coherence-based Pseudo Labeling and Cooperative Unfolding Network (NeurIPS 2024 · similarity 0.88)
- Prior-guided Hierarchical Harmonization Network for Efficient Image Dehazing (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.