Research map / Video / Video generation
DiffHDR: Re-Exposing LDR Videos with Video Diffusion Models
Zhengming Yu, Li Ma, Mingming He, Leo Isikdogan, Yuancheng Xu, Dmitriy Smirnov, Pablo Salamanca, Dao Mi, Pablo Delgado, Ning Yu, Julien Philip, Xin Li and 2 more
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 Log-Gamma mapping instead of linear encoding (ablation) | DiffHDR · VAE reconstruction of HDR | PSNR: 22.16 -> 32.86 | Improved |
| add Log-Gamma mapping instead of pure log mapping (ablation) | DiffHDR · VAE reconstruction of HDR | PSNR: 14.61 -> 32.86 | Improved |
| add gamma compression to log mapping (ablation) | DiffHDR · VAE reconstruction of HDR | PSNR: 25.38 -> 32.86 | Improved |
| add gamma compression to log mapping (ablation) | DiffHDR · VAE reconstruction of HDR | LPIPS: 0.34 -> 0.15 | Improved |
| add Log-Gamma mapping instead of linear encoding (ablation) | DiffHDR · VAE reconstruction of HDR | LPIPS: 0.28 -> 0.15 | Improved |
| add exposure-aware data augmentation to training (ablation) | DiffHDR · Polyhaven synthetic video | FovVideoVDP: 7.57 -> 7.65 | Improved |
| add exposure-aware data augmentation to training (ablation) | DiffHDR · Polyhaven synthetic video | MUSIQ: 59.86 -> 60.02 | Improved |
| add luminance mask guidance (ablation) | DiffHDR · Polyhaven synthetic video | FovVideoVDP: 7.58 -> 7.65 | Improved |
| add luminance mask guidance (ablation) | DiffHDR · Polyhaven synthetic video | MUSIQ: 59.42 -> 60.02 | Improved |
| add luminance mask guidance (ablation) | DiffHDR · Polyhaven synthetic video | CLIPIQA: 0.48 -> 0.50 | Improved |
| add context-focused prompting over global prompting (ablation) | DiffHDR · qualitative sun example | visual structure | Improved |
| finetune the video VAE on HDR data (ablation) | DiffHDR · HDR reconstruction | VAE reconstruction quality | Hurt |
Closest papers by meaning
- Single Shot HDR Recovery via a Video Diffusion Prior (NeurIPS 2026 · similarity 0.90)
- Generating Content for HDR Deghosting from Frequency View (CVPR 2024 · similarity 0.89)
- Towards Real-World HDR Video Reconstruction: A Large-Scale Benchmark Dataset and A Two-Stage Alignment Network (CVPR 2024 · similarity 0.89)
- LEDiff: Latent Exposure Diffusion for HDR Generation (CVPR 2025 · similarity 0.89)
- High Dynamic Range Novel View Synthesis with Single Exposure (ICML 2025 · similarity 0.88)
- GaussHDR: High Dynamic Range Gaussian Splatting via Learning Unified 3D and 2D Local Tone Mapping (CVPR 2025 · similarity 0.88)
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.
