DiffHDR: Re-Exposing LDR Videos with Video Diffusion Models
cs.CV, cs.AI, cs.GR
Submitted: 2026-04-07
Updated: 2026-08-31
Comments: 28 pages, 13 figures. Accepted to ECCV 2026. Project page: https://eyeline-labs.github.io/DiffHDR/
Project page: https://eyeline-labs.github.io/DiffHDR
License: http://creativecommons.org/licenses/by-nc-sa/4.0/
The gist: Most digital videos are stored in 8-bit low dynamic range (LDR) formats, where much of the original high dynamic range (HDR) scene radiance is lost due to saturation and quantization.
Terminology
Abstract
Most digital videos are stored in 8-bit low dynamic range (LDR) formats, where much of the original high dynamic range (HDR) scene radiance is lost due to saturation and quantization. This loss of highlight and shadow detail precludes mapping accurate luminance to HDR displays and limits meaningful re-exposure in post-production workflows. Although techniques have been proposed to convert LDR images to HDR through dynamic range expansion, they struggle to restore realistic detail in the over- and underexposed regions. To address this, we present DiffHDR, a framework that formulates LDR-to-HDR conversion as a generative radiance inpainting task within the latent space of a video diffusion model. By operating in Log-Gamma color space, DiffHDR leverages spatio-temporal generative priors from a pretrained video diffusion model to synthesize plausible HDR radiance in over- and underexposed regions while recovering the continuous scene radiance of the quantized pixels. Our framework further enables controllable LDR-to-HDR video conversion guided by text prompts or reference images. To address the scarcity of paired HDR video data, we develop a pipeline that synthesizes high-quality HDR video training data from static HDRI maps. Extensive experiments demonstrate that DiffHDR significantly outperforms state-of-the-art approaches in radiance fidelity and temporal stability, producing realistic HDR videos with considerable latitude for re-exposure.
Sources
- Cosmos World Foundation Model Platform for Physical AI
- Bracket Diffusion: HDR Image Generation by Consistent LDR Denoising
- Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets
- Semantic Aware Diffusion Inverse Tone Mapping
- LTX-Video: Realtime Video Latent Diffusion
- Classifier-Free Diffusion Guidance
- VChain: Chain-of-Visual-Thought for Reasoning in Video Generation
- VACE: All-in-One Video Creation and Editing
- SAFNet: Selective Alignment Fusion Network for Efficient HDR Imaging
- Flow Matching for Generative Modeling
- Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
- Decoupled Weight Decay Regularization
- HDR-VDP-3: A multi-metric for predicting image differences, quality and contrast distortions in high dynamic range and regular content
- Gemini: A Family of Highly Capable Multimodal Models
- Wan: Open and Advanced Large-Scale Video Generative Models
- 360-Degree Panorama Generation from Few Unregistered NFoV Images
- X2HDR: HDR Image Generation in a Perceptually Uniform Space
- Virtually Being: Customizing Camera-Controllable Video Diffusion Models with Multi-View Performance Captures
- Qwen3 Technical Report
- CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models