Research map / Image generation / Image restoration
Learning Continuous Exposure Value Representations for Single-Image HDR Reconstruction
Su-Kai Chen, Hung-Lin Yen, Yu-Lun Liu, Min-Hung Chen, Hou-Ning Hu, Wen-Hsiao Peng, Yen-Yu Lin
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 intensity transformation module to the LDR stack generator (ablation) | CEVR · VDS HDR reconstruction | PSNR: 32.52 -> 34.20 | Improved |
| Add continuous stack (13 images with half-step EVs) (ablation) | CEVR with intensity transformation · VDS HDR reconstruction | PSNR: 34.20 -> 34.47 | Improved |
| Add cycle training (ablation) | CEVR with intensity transformation and continuous stack · VDS HDR reconstruction | PSNR: 34.47 -> 34.67 | Improved |
| Add cycle training (ablation) | CEVR · VDS LDR stack EV+3 | PSNR: 33.90 -> 34.34 | Improved |
| Add cycle training for unseen EVs (ablation) | CEVR · Hold-out EV-1 | PSNR: 27.75 -> 33.77 | Improved |
| Add cycle training for unseen EVs (ablation) | CEVR · Hold-out EV+1 | PSNR: 33.37 -> 36.96 | Improved |
| Use CEVR instead of Deep recursive HDRI on VDS | Single-image HDR reconstruction · VDS | PSNR with RH's tone mapping: 32.99 -> 34.67 | Improved |
| Use CEVR instead of Deep recursive HDRI on blind HDREye | Single-image HDR reconstruction · HDREye | PSNR with RH's tone mapping: 26.28 -> 26.54 | Improved |
| Use CEVR on severely over-exposed saturated regions | CEVR · Failure cases | qualitative | No clear effect |
Closest papers by meaning
- Single Shot HDR Recovery via a Video Diffusion Prior (NeurIPS 2026 · similarity 0.88)
- High Dynamic Range Novel View Synthesis with Single Exposure (ICML 2025 · similarity 0.86)
- Generating Content for HDR Deghosting from Frequency View (CVPR 2024 · similarity 0.86)
- Towards Real-World HDR Video Reconstruction: A Large-Scale Benchmark Dataset and A Two-Stage Alignment Network (CVPR 2024 · similarity 0.84)
- Zero-Shot Structure-Preserving Diffusion Model for High Dynamic Range Tone Mapping (CVPR 2024 · similarity 0.84)
- Self-Supervised High Dynamic Range Imaging with Multi-Exposure Images in Dynamic Scenes (ICLR 2024 · 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.
