Research map / Image generation / Image restoration
Content Adaptive Latents and Decoder for Neural Image Compression
Guanbo Pan, Guo Lu, Zhihao Hu, Dong Xu
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 content adaptive feature transformation (CAFT) to the decoder (ablation) | non-context baseline · Tecnick | BDBR (%): -9.47 | Improved |
| add content adaptive channel dropping (CACD) to the latents (ablation) | non-context baseline · Tecnick | BDBR (%): -1.51 | Improved |
| add CACD on top of CAFT (ablation) | non-context baseline · Tecnick | BDBR (%): -9.47 -> -11.08 | Improved |
| combine content adaptive methods with SGA (ablation) | non-context baseline · Kodak | BDBR (%): -15.17 -> -26.52 | Improved |
| combine content adaptive methods with SGA (ablation) | non-context baseline · Tecnick | BDBR (%): -18.72 -> -28.51 | Improved |
| use content adaptive methods alone instead of SGA's encoder-side updating | non-context baseline · Kodak | BDBR (%): -15.17 -> -11.51 | Hurt |
| add content adaptive methods to video codec DVC* | DVC* · HEVC Class C | PSNR: about 0.1 dB at middle bit-rate, about 0.3 dB at other bit-rates | Improved |
Closest papers by meaning
- Robustly overfitting latents for flexible neural image compression (NeurIPS 2024 · similarity 0.86)
- Neural Image Compression: Generalization, Robustness, and Spectral Biases (NeurIPS 2023 · similarity 0.85)
- Controllable Distortion-Perception Tradeoff Through Latent Diffusion for Neural Image Compression (AAAI 2025 · similarity 0.84)
- Test-time Adaptation for Image Compression with Distribution Regularization (ICLR 2025 · similarity 0.84)
- Diversify, Contextualize, and Adapt: Efficient Entropy Modeling for Neural Image Codec (NeurIPS 2024 · similarity 0.84)
- C3: High-Performance and Low-Complexity Neural Compression from a Single Image or Video (CVPR 2024 · similarity 0.83)
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.
