HDR Video Generation via Latent Alignment with Logarithmic Encoding
This work simplifies HDR generation for video, avoiding the need to retrain or redesign generative models, which is beneficial for practitioners in computer vision and graphics.
The authors show that high dynamic range (HDR) video generation can be achieved by leveraging pretrained generative models with minimal adaptation, using logarithmic encoding to align HDR imagery with the latent space and a training strategy with camera-mimicking degradations. They achieve high-quality results across diverse scenes and challenging lighting conditions.
High dynamic range (HDR) imagery offers a rich and faithful representation of scene radiance, but remains challenging for generative models due to its mismatch with the bounded, perceptually compressed data on which these models are trained. A natural solution is to learn new representations for HDR, which introduces additional complexity and data requirements. In this work, we show that HDR generation can be achieved in a much simpler way by leveraging the strong visual priors already captured by pretrained generative models. We observe that a logarithmic encoding widely used in cinematic pipelines maps HDR imagery into a distribution that is naturally aligned with the latent space of these models, enabling direct adaptation via lightweight fine-tuning without retraining an encoder. To recover details that are not directly observable in the input, we further introduce a training strategy based on camera-mimicking degradations that encourages the model to infer missing high dynamic range content from its learned priors. Combining these insights, we demonstrate high-quality HDR video generation using a pretrained video model with minimal adaptation, achieving strong results across diverse scenes and challenging lighting conditions. Our results indicate that HDR, despite representing a fundamentally different image formation regime, can be handled effectively without redesigning generative models, provided that the representation is chosen to align with their learned priors.