Research map / Image generation / Image restoration
Raw Image Reconstruction With Learned Compact Metadata
Yufei Wang, Yi Yu, Wenhan Yang, Lanqing Guo, Lap-Pui Chau, Alex C. Kot, Bihan Wen
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 |
|---|---|---|---|
| learn a compact latent-space metadata representation end-to-end instead of sampling raw pixels | Raw image reconstruction · AdobeFiveK | PSNR: 56.72 -> 58.14 | Improved |
| add learned compact latent-space metadata (ablation) | Ours · AdobeFiveK | PSNR: 53.03 -> 58.14 | Improved |
| add saved channel means m(v) to the hyper-prior metadata (ablation) | Ours · NUS, mean | PSNR: 58.66 -> 58.79 | Improved |
| add saved channel means m(v) to the hyper-prior metadata (ablation) | Ours · NUS, mean | bpp: 2.92e-4 -> 2.89e-4 | Improved |
| replace the sRGB-guided context model with the checkerboard context model (ablation) | Ours · NUS, compressed JPEG images | bpp | Hurt |
| use already decoded latent features as context for estimating the remaining latent distribution (ablation) | sRGB-guided context model · Raw image reconstruction | bpp | Improved |
| adapt metadata bit allocation to image content in latent space | Ours · Raw image reconstruction | PSNR | Improved |
Closest papers by meaning
- Beyond Learned Metadata-Based Raw Image Reconstruction (IJCV 2024 · similarity 0.96)
- Learning Raw Image Reconstruction-Aware Deep Image Compressors (TPAMI 2019 · similarity 0.91)
- Compress Clean Signal from Noisy Raw Image: A Self-Supervised Approach (ICML 2024 · similarity 0.88)
- Leveraging Frame Affinity for sRGB-to-RAW Video De-rendering (CVPR 2024 · similarity 0.86)
- Ultra Lowrate Image Compression with Semantic Residual Coding and Compression-aware Diffusion (ICML 2025 · similarity 0.86)
- GLIC: General Format Learned Image Compression (AAAI 2025 · similarity 0.84)
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.
