RawGen: Learning Camera Raw Image Generation

• URL: http://arxiv.org/abs/2604.00093v1
• Date: Tue, 31 Mar 2026 18:12:48 GMT
• Title: RawGen: Learning Camera Raw Image Generation
• Abstract summary: RawGen is the first diffusion-based framework enabling text-to-raw generation for arbitrary target cameras.<n>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.<n>We demonstrate RawGen's superior performance over traditional inverse-ISP methods that assume a fixed ISP.
• Score: 30.54177507076165
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• 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 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.

Related papers

• Dark-ISP: Enhancing RAW Image Processing for Low-Light Object Detection [22.292648672901066]
  Low-light Object detection is crucial for many real-world applications but remains challenging due to degraded image quality.<n>We propose a lightweight and self-adaptive Image Signal Processing (ISP) plugin, Dark-ISP, which directly processes Bayer RAW images in dark environments.<n>Our method outperforms state-of-the-art RGB- and RAW-based detection approaches, achieving superior results with minimal parameters in challenging low-light environments.
  arXiv  Detail & Related papers  (2025-09-11T06:44:43Z)
• RAW-Adapter: Adapting Pre-trained Visual Model to Camera RAW Images and A Benchmark [58.47710845549269]
  RAW-Adapter is a novel framework that incorporates learnable ISP modules as input-level adapters to adjust RAW inputs.<n> RAW-Adapter serves as a general framework applicable to various computer vision frameworks.<n>We introduce RAW-Bench, which incorporates 17 types of RAW-based common corruptions.
  arXiv  Detail & Related papers  (2025-03-21T10:37:42Z)
• Beyond RGB: Adaptive Parallel Processing for RAW Object Detection [5.36869872375791]
  Raw Adaptation Module (RAM) is a module designed to replace the traditional Image Signal Processing (ISP)<n>Our approach outperforms RGB-based methods and achieves state-of-the-art results across diverse RAW image datasets.
  arXiv  Detail & Related papers  (2025-03-17T13:36:49Z)
• Unveiling Hidden Details: A RAW Data-Enhanced Paradigm for Real-World Super-Resolution [56.98910228239627]
  Real-world image super-resolution (Real SR) aims to generate high-fidelity, detail-rich high-resolution (HR) images from low-resolution (LR) counterparts. Existing Real SR methods primarily focus on generating details from the LR RGB domain, often leading to a lack of richness or fidelity in fine details. We pioneer the use of details hidden in RAW data to complement existing RGB-only methods, yielding superior outputs.
  arXiv  Detail & Related papers  (2024-11-16T13:29:50Z)
• A Learnable Color Correction Matrix for RAW Reconstruction [19.394856071610604]
  We introduce a learnable color correction matrix (CCM) to approximate the complex inverse image signal processor (ISP) Experimental results demonstrate that simulated RAW (simRAW) images generated by our method provide performance improvements equivalent to those produced by more complex inverse ISP methods.
  arXiv  Detail & Related papers  (2024-09-04T07:46:42Z)
• RAW-Adapter: Adapting Pre-trained Visual Model to Camera RAW Images [51.68432586065828]
  We introduce RAW-Adapter, a novel approach aimed at adapting sRGB pre-trained models to camera RAW data. Raw-Adapter comprises input-level adapters that employ learnable ISP stages to adjust RAW inputs, as well as model-level adapters to build connections between ISP stages and subsequent high-level networks.
  arXiv  Detail & Related papers  (2024-08-27T06:14:54Z)
• Rawformer: Unpaired Raw-to-Raw Translation for Learnable Camera ISPs [53.68932498994655]
  This paper introduces a novel method for unpaired learning of raw-to-raw translation across diverse cameras. It accurately maps raw images captured by a certain camera to the target camera, facilitating the generalization of learnable ISPs to new unseen cameras. Our method demonstrates superior performance on real camera datasets, achieving higher accuracy compared to previous state-of-the-art techniques.
  arXiv  Detail & Related papers  (2024-04-16T16:17:48Z)
• Raw Image Reconstruction with Learned Compact Metadata [61.62454853089346]
  We propose a novel framework to learn a compact representation in the latent space serving as the metadata in an end-to-end manner. We show how the proposed raw image compression scheme can adaptively allocate more bits to image regions that are important from a global perspective.
  arXiv  Detail & Related papers  (2023-02-25T05:29:45Z)
• Efficient Visual Computing with Camera RAW Snapshots [41.9863557302409]
  Conventional cameras capture image irradiance on a sensor and convert it to RGB images using an image signal processor (ISP) One can argue that since RAW images contain all the captured information, the conversion of RAW to RGB using an ISP is not necessary for visual computing. We propose a novel $rho$-Vision framework to perform high-level semantic understanding and low-level compression using RAW images.
  arXiv  Detail & Related papers  (2022-12-15T12:54:21Z)
• Reversed Image Signal Processing and RAW Reconstruction. AIM 2022 Challenge Report [109.2135194765743]
  This paper introduces the AIM 2022 Challenge on Reversed Image Signal Processing and RAW Reconstruction. We aim to recover raw sensor images from the corresponding RGBs without metadata and, by doing this, "reverse" the ISP transformation.
  arXiv  Detail & Related papers  (2022-10-20T10:43:53Z)
• Model-Based Image Signal Processors via Learnable Dictionaries [6.766416093990318]
  Digital cameras transform sensor RAW readings into RGB images by means of their Image Signal Processor (ISP) Recent approaches have attempted to bridge this gap by estimating the RGB to RAW mapping. We present a novel hybrid model-based and data-driven ISP that is both learnable and interpretable.
  arXiv  Detail & Related papers  (2022-01-10T08:36:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.