Research map / Image generation / Image restoration
CADC: Content Adaptive Diffusion-Based Generative Image Compression
Xihua Sheng, Lingyu Zhu, Tianyu Zhang, Dong Liu, Shiqi Wang, Jing 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 Uncertainty-Guided Adaptive Quantization (ablation) | CADC diffusion codec (Kodak) · Kodak | LPIPS BD-rate: BD-rate 0.00% -> -3.7% | Improved |
| add UGAQ (ablation) | CADC diffusion codec (Kodak) · Kodak | DISTS BD-rate: BD-rate 0.00% -> -2.7% | Improved |
| add Auxiliary Decoder-Guided Information Concentration (ablation) | CADC diffusion codec (Kodak) · Kodak | LPIPS BD-rate: BD-rate -3.7% -> -5.3% | Improved |
| add ADGIC (ablation) | CADC diffusion codec (Kodak) · Kodak | DISTS BD-rate: BD-rate -2.7% -> -3.5% | Improved |
| add Bitrate-Free Adaptive Textual Conditioning (ablation) | CADC diffusion codec (Kodak) · Kodak | LPIPS BD-rate: BD-rate -5.3% -> -6.8% | Improved |
| add BFATC (ablation) | CADC diffusion codec (Kodak) · Kodak | DISTS BD-rate: BD-rate -3.5% -> -5.5% | Improved |
| CADC versus other diffusion codecs (DiffEIC, ResULIC, MKIC, OSCAR, StableCodec) | CADC · Kodak, DIV2K Val, CLIC 2020 Test | LPIPS, DISTS, FID, KID | Improved |
Closest papers by meaning
- Bridging the Gap between Gaussian Diffusion Models and Universal Quantization for Image Compression (CVPR 2025 · similarity 0.90)
- One-Step Diffusion-Based Image Compression with Semantic Distillation (NeurIPS 2025 · similarity 0.89)
- Decouple Distortion from Perception: Region Adaptive Diffusion for Extreme-low Bitrate Perception Image Compression (CVPR 2025 · similarity 0.88)
- OSCAR: One-Step Diffusion Codec Across Multiple Bit-rates (NeurIPS 2025 · similarity 0.87)
- Ultra Lowrate Image Compression with Semantic Residual Coding and Compression-aware Diffusion (ICML 2025 · similarity 0.87)
- Progressive Compression with Universally Quantized Diffusion Models (ICLR 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.
