Research map / Image generation / Image restoration
UnModNet: Learning to Unwrap a Modulo Image for High Dynamic Range Imaging
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| iterative binary rollover mask prediction instead of directly predicting K (ablation) | UnModNet · Synthetic HDR data | PSNR: 21.82 -> 28.51 | Helped |
| add modulo edge separator (ablation) | UnModNet · Synthetic HDR data | Q-Score: 46.66 -> 54.78 | Helped |
| add Laplace-based residual learning of modulo edges (ablation) | UnModNet · Synthetic HDR data | PSNR: 26.06 -> 28.51 | Helped |
| two-stage training instead of end-to-end training (ablation) | UnModNet · Synthetic HDR data | PSNR: 27.08 -> 28.51 | Helped |
| unwrap modulo image with UnModNet instead of MRF-based unwrapping | modulo image HDR reconstruction · Synthetic HDR data | PSNR: 8.88 -> 28.51 | Helped |
| UnModNet on modulo input vs single-image LDR HDR methods (HDRCNN best) | HDR reconstruction · Synthetic HDR data | PSNR: 22.74 -> 28.51 | Helped |
Closest papers by meaning
- MoDGS: Dynamic Gaussian Splatting from Casually-captured Monocular Videos with Depth Priors (ICLR 2025 · similarity 0.85)
- UltraFusion: Ultra High Dynamic Imaging using Exposure Fusion (CVPR 2025 · similarity 0.84)
- UltraLED: Learning to See Everything in Ultra-High Dynamic Range Scenes (NeurIPS 2025 · similarity 0.84)
- Self-Supervised High Dynamic Range Imaging with Multi-Exposure Images in Dynamic Scenes (ICLR 2024 · similarity 0.84)
- GaussHDR: High Dynamic Range Gaussian Splatting via Learning Unified 3D and 2D Local Tone Mapping (CVPR 2025 · similarity 0.83)
- Generating Content for HDR Deghosting from Frequency View (CVPR 2024 · similarity 0.83)
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.