First generative model capable of synthesizing physically consistent 'raw' camera sensor data from text prompts or sRGB images.
April 2, 2026
Original Paper
RawGen: Learning Camera Raw Image Generation
arXiv · 2604.00093
The Takeaway
This solves a major data scarcity bottleneck for low-level computer vision tasks like denoising and ISP design. Researchers can now generate high-fidelity synthetic raw datasets for any arbitrary camera hardware.
From the abstract
Cameras capture scene-referred linear raw images, which are processed by onboard image signal processors (ISPs) into display-referred 8-bit sRGB outputs. Although raw data is more faithful for low-level vision tasks, collecting large-scale raw datasets remains a major bottleneck, as existing datasets are limited and tied to specific camera hardware. Generative models offer a promising way to address this scarcity -- however, existing diffusion frameworks are designed to synthesize photo-finished