Research map / Image generation / Image restoration
Learned HDR Image Compression for Perceptually Optimal Storage and Display
Peibei Cao, HAOYU CHEN, Jingzhe Ma, Yu-Chieh Yuan, Zhiyong Xie, Xin Xie, Haiqing Bai, Kede Ma
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 |
|---|---|---|---|
| End-to-end learned two-bitstream HDR compression instead of manual layer decomposition | HDR image compression · Poly Haven HDR test | BD-Quality HDR-VDP-3: 0.1703 -> 1.1202 (vs OoDHDR-codec) | Improved |
| Use the inverse display model based HDR distortion d_ADISTS instead of other perceptual encodings or TMO front-ends (ablation) | EPIC-HDR loss · Poly Haven HDR test | HDR rate-distortion | Improved |
| Add HDR side information bitstream (about 0.04 to 0.05 bpp) (ablation) | EPIC-HDR · Poly Haven HDR test | HDR rate-distortion: side info costs about 0.04 to 0.05 bpp | Improved |
| Optimize LDR output with TMQI instead of NLPD (ablation) | EPIC-HDR LDR branch · Poly Haven HDR test | NLPD | Hurt |
| Add multi-exposure fusion over four maximum luminances to automate EPIC-HDR (ablation) | EPIC-HDR · Poly Haven HDR test | BD-Quality PU21-PSNR with CRF correction: 7.9145 -> 9.7701 (PU21-PSNR); 1.1202 -> 0.9521 (HDR-VDP-3) | Mixed |
Closest papers by meaning
- Perceptual Assessment and Optimization of HDR Image Rendering (CVPR 2024 · similarity 0.89)
- High Dynamic Range Video Compression: A Large-Scale Benchmark Dataset and A Learned Bit-depth Scalable Compression Algorithm (CVPR 2025 · similarity 0.88)
- Single Shot HDR Recovery via a Video Diffusion Prior (NeurIPS 2026 · similarity 0.87)
- Generating Content for HDR Deghosting from Frequency View (CVPR 2024 · similarity 0.87)
- Zero-Shot Structure-Preserving Diffusion Model for High Dynamic Range Tone Mapping (CVPR 2024 · similarity 0.87)
- Towards image compression with perfect realism at ultra-low bitrates (ICLR 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.
