Research map / Image generation / Image restoration
Exposure-Aware Dynamic Weighted Learning for Single-Shot HDR Imaging
An Gia Vien, Chul Lee
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 FusionNet to combine DINet and ExRNet outputs (ablation) | restoration · Kalantari | pu-PSNR: 44.84 -> 47.72 | Improved |
| use ExRNet instead of DINet (ablation) | restoration · Kalantari | pu-MSSSIM: 0.9969 -> 0.9965 | Hurt |
| use ExRNet instead of DINet (ablation) | restoration · Kalantari | pu-PSNR: 44.84 -> 46.96 | Improved |
| add exposure-aware mask M to DINet (ablation) | DINet · Kalantari | pu-PSNR: 38.18 -> 44.84 | Improved |
| add exposure-aware mask M to ExRNet (ablation) | ExRNet · Kalantari | pu-PSNR: 42.86 -> 46.96 | Improved |
| add exposure-aware mask M to ExRNet (ablation) | ExRNet · Kalantari | pu-MSSSIM: 0.9893 -> 0.9965 | Improved |
| add channel fusion in MEF block (ablation) | ExRNet · Kalantari | pu-PSNR: 46.05 -> 46.67 | Improved |
| add spatial fusion in MEF block (ablation) | ExRNet · Kalantari | pu-PSNR: 46.05 -> 46.63 | Improved |
| add both channel and spatial fusion (ablation) | ExRNet · Kalantari | pu-PSNR: 46.05 -> 46.85 | Improved |
| add element-wise weighting A(l) (ablation) | ExRNet · Kalantari | pu-PSNR: 46.85 -> 46.96 | Improved |
| use Zhang et al. demosaicing instead of Adams (ablation) | EDWL · Kalantari | pu-PSNR: 45.22 -> 46.17 | Improved |
| use Zhang et al. demosaicing instead of Malvar et al. (ablation) | EDWL · Kalantari | pu-PSNR: 44.99 -> 46.17 | Improved |
Closest papers by meaning
- Single Shot HDR Recovery via a Video Diffusion Prior (NeurIPS 2026 · similarity 0.90)
- Color Event Enhanced Single-Exposure HDR Imaging (AAAI 2024 · similarity 0.90)
- Self-Supervised High Dynamic Range Imaging with Multi-Exposure Images in Dynamic Scenes (ICLR 2024 · similarity 0.90)
- High Dynamic Range Novel View Synthesis with Single Exposure (ICML 2025 · similarity 0.88)
- Neural Exposure Fusion for High-Dynamic Range Object Detection (CVPR 2024 · similarity 0.88)
- EvHDR-NeRF: Building High Dynamic Range Radiance Fields with Single Exposure Images and Events (AAAI 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.
