RawGen: Learning Camera Raw Image Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kim, Dongyoung, Lee, Junyong, Punnappurath, Abhijith, Afifi, Mahmoud, Han, Sangmin, Levinshtein, Alex, Brown, Michael S.
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915904138248192
author Kim, Dongyoung
Lee, Junyong
Punnappurath, Abhijith
Afifi, Mahmoud
Han, Sangmin
Levinshtein, Alex
Brown, Michael S.
author_facet Kim, Dongyoung
Lee, Junyong
Punnappurath, Abhijith
Afifi, Mahmoud
Han, Sangmin
Levinshtein, Alex
Brown, Michael S.
contents 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 sRGB images rather than physically consistent linear representations. This paper presents RawGen, to our knowledge the first diffusion-based framework enabling text-to-raw generation for arbitrary target cameras, alongside sRGB-to-raw inversion. RawGen leverages the generative priors of large-scale sRGB diffusion models to synthesize physically meaningful linear outputs, such as CIE XYZ or camera-specific raw representations, via specialized processing in latent and pixel spaces. To handle unknown and diverse ISP pipelines and photo-finishing effects in diffusion-model training data, we build a many-to-one inverse-ISP dataset where multiple sRGB renditions of the same scene generated using diverse ISP parameters are anchored to a common scene-referred target. Fine-tuning a conditional denoiser and specialized decoder on this dataset allows RawGen to obtain camera-centric linear reconstructions that effectively invert the rendering pipeline. We demonstrate RawGen's superior performance over traditional inverse-ISP methods that assume a fixed ISP. Furthermore, we show that augmenting training pipelines with RawGen's scalable, text-driven synthetic data can benefit downstream low-level vision tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2604_00093
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle RawGen: Learning Camera Raw Image Generation
Kim, Dongyoung
Lee, Junyong
Punnappurath, Abhijith
Afifi, Mahmoud
Han, Sangmin
Levinshtein, Alex
Brown, Michael S.
Computer Vision and Pattern Recognition
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 sRGB images rather than physically consistent linear representations. This paper presents RawGen, to our knowledge the first diffusion-based framework enabling text-to-raw generation for arbitrary target cameras, alongside sRGB-to-raw inversion. RawGen leverages the generative priors of large-scale sRGB diffusion models to synthesize physically meaningful linear outputs, such as CIE XYZ or camera-specific raw representations, via specialized processing in latent and pixel spaces. To handle unknown and diverse ISP pipelines and photo-finishing effects in diffusion-model training data, we build a many-to-one inverse-ISP dataset where multiple sRGB renditions of the same scene generated using diverse ISP parameters are anchored to a common scene-referred target. Fine-tuning a conditional denoiser and specialized decoder on this dataset allows RawGen to obtain camera-centric linear reconstructions that effectively invert the rendering pipeline. We demonstrate RawGen's superior performance over traditional inverse-ISP methods that assume a fixed ISP. Furthermore, we show that augmenting training pipelines with RawGen's scalable, text-driven synthetic data can benefit downstream low-level vision tasks.
title RawGen: Learning Camera Raw Image Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.00093