What an 8-Bit Frame Can and Cannot Say About the Scene Behind It
Research on the limits of reconstructing HDR from clipped images.
In-house tools / Model
Radiometric Dynamic-Range Conditioning for HDR-Aware Diffusion Models.
Convert SDR images to HDR, or use trained decoders to generate scene-linear OpenEXR directly from diffusion models.
Research on the limits of reconstructing HDR from clipped images.
Download SDR-to-HDR models, a temporal refiner and HDR decoders for eight diffusion backbones.
Enable rudra_decoder in Radiance’s HDR VAE Decode node to output scene-linear EXR.
What’s in the release
Reconstruct HDR from SDR footage with image models and a temporal refiner for sequences.
shadow_v1 · s2 · s3 · image_v5 · image_v6 · temporal_v1
Generate scene-linear HDR directly, without a tone-mapped intermediate.
Flux.1 · Flux.2 · Flux.2 Klein · SDXL · Qwen-Image · Z-Image · Wan · LTX-Video — full + turbo
An SDR image can lose highlight detail through clipping. Expanding its brightness alone cannot restore that detail.
RUDRA uses HDR training references to infer plausible highlights. Reconstruction estimates missing detail rather than recovering a unique original scene.
The reconstructed result adds a defined sun disc and flare while retaining foreground detail.
Cloud structure and a warm horizon appear in the reconstruction while the road and foliage retain depth.
The reconstruction adds shape within bright clouds while retaining blue in the sky.
The paper explains the limits of HDR reconstruction from an 8-bit image.
Generate scene-linear OpenEXR directly from supported diffusion models.
Model weights, reference code and Radiance integration are available under Apache 2.0.