AI Paper Atlas

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

ECCV 2026 · Video › Video generation · approach: Efficient video diffusion models · 5 citations (OpenAlex)

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 changedWhereMeasuredEffect
add Log-Gamma mapping instead of linear encoding (ablation)DiffHDR · VAE reconstruction of HDRPSNR: 22.16 -> 32.86Improved
add Log-Gamma mapping instead of pure log mapping (ablation)DiffHDR · VAE reconstruction of HDRPSNR: 14.61 -> 32.86Improved
add gamma compression to log mapping (ablation)DiffHDR · VAE reconstruction of HDRPSNR: 25.38 -> 32.86Improved
add gamma compression to log mapping (ablation)DiffHDR · VAE reconstruction of HDRLPIPS: 0.34 -> 0.15Improved
add Log-Gamma mapping instead of linear encoding (ablation)DiffHDR · VAE reconstruction of HDRLPIPS: 0.28 -> 0.15Improved
add exposure-aware data augmentation to training (ablation)DiffHDR · Polyhaven synthetic videoFovVideoVDP: 7.57 -> 7.65Improved
add exposure-aware data augmentation to training (ablation)DiffHDR · Polyhaven synthetic videoMUSIQ: 59.86 -> 60.02Improved
add luminance mask guidance (ablation)DiffHDR · Polyhaven synthetic videoFovVideoVDP: 7.58 -> 7.65Improved
add luminance mask guidance (ablation)DiffHDR · Polyhaven synthetic videoMUSIQ: 59.42 -> 60.02Improved
add luminance mask guidance (ablation)DiffHDR · Polyhaven synthetic videoCLIPIQA: 0.48 -> 0.50Improved
add context-focused prompting over global prompting (ablation)DiffHDR · qualitative sun examplevisual structureImproved
finetune the video VAE on HDR data (ablation)DiffHDR · HDR reconstructionVAE reconstruction qualityHurt

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy