Research map / Image generation / Image restoration
Coarse-to-Fine Hyper-Prior Modeling for Learned Image Compression
Yueyu Hu, Wenhan Yang, Jiaying Liu
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 signal-preserving hyper transform with extra hyper-prior layer (ablation) | Hyper-prior (Balle et al. 2018) · Kodak | R-D (PSNR vs bpp) | Improved |
| add extra hyper layer using original transforms (ablation) | Hyper-prior (Balle et al. 2018) · Kodak | R-D (PSNR vs bpp) | No clear effect |
| add Information Aggregation Reconstruction sub-network (ablation) | multi-layer hyper-prior model · Kodak | R-D (PSNR vs bpp) | Improved |
| replace context model with coarse-to-fine hyper-prior | learned image codec · large 1512x2040 images | GPU acceleration ratio (encoder): 163.3% vs 128.1% | Improved |
| coarse-to-fine hyper-prior vs context model + hyper-prior | learned image codec · Tecnick | R-D (PSNR vs bpp) | Improved |
Closest papers by meaning
- Joint Autoregressive and Hierarchical Priors for Learned Image Compression (NeurIPS 2018 · similarity 0.89)
- Learning End-to-End Lossy Image Compression: A Benchmark (TPAMI 2021 · similarity 0.89)
- Learned Image Compression with Dictionary-based Entropy Model (CVPR 2025 · similarity 0.86)
- Robustly overfitting latents for flexible neural image compression (NeurIPS 2024 · similarity 0.86)
- Ultra Lowrate Image Compression with Semantic Residual Coding and Compression-aware Diffusion (ICML 2025 · similarity 0.86)
- Diversify, Contextualize, and Adapt: Efficient Entropy Modeling for Neural Image Codec (NeurIPS 2024 · 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.
