RDDM: Practicing RAW Domain Diffusion Model for Real-world Image Restoration

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Chen, Yan, Wen, Yi, Li, Wei, Liu, Junchao, Guo, Yong, Hu, Jie, Chen, Xinghao
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908803754098688
author Chen, Yan
Wen, Yi
Li, Wei
Liu, Junchao
Guo, Yong
Hu, Jie
Chen, Xinghao
author_facet Chen, Yan
Wen, Yi
Li, Wei
Liu, Junchao
Guo, Yong
Hu, Jie
Chen, Xinghao
contents We present the RAW domain diffusion model (RDDM), an end-to-end diffusion model that restores photo-realistic images directly from the sensor RAW data. While recent sRGB-domain diffusion methods achieve impressive results, they are caught in a dilemma between high fidelity and image generation. These models process lossy sRGB inputs and neglect the accessibility of the sensor RAW images in many scenarios, e.g., in image and video capturing in edge devices, resulting in sub-optimal performance. RDDM obviates this limitation by directly restoring images in the RAW domain, replacing the conventional two-stage image signal processing (ISP)->Image Restoration (IR) pipeline. However, a simple adaptation of pre-trained diffusion models to the RAW domain confronts many challenges. To this end, we propose: (1) a RAW-domain VAE (RVAE), encoding sensor RAW and decoding it into an enhanced linear domain image, to solve the out-of-distribution (OOD) issues between the different domain distributions; (2) a configurable multi-bayer (CMB) LoRA module, adapting diverse RAW Bayer patterns such as RGGB, BGGR, etc. To compensate for the deficiency in the dataset, we develop a scalable data synthesis pipeline synthesizing RAW LQ-HQ pairs from existing sRGB datasets for large-scale training. Extensive experiments demonstrate RDDM's superiority over state-of-the-art sRGB diffusion methods, yielding higher fidelity results with fewer artifacts. Codes will be publicly available at https://github.com/YanCHEN-fr/RDDM.
format Preprint
id arxiv_https___arxiv_org_abs_2508_19154
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RDDM: Practicing RAW Domain Diffusion Model for Real-world Image Restoration
Chen, Yan
Wen, Yi
Li, Wei
Liu, Junchao
Guo, Yong
Hu, Jie
Chen, Xinghao
Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
We present the RAW domain diffusion model (RDDM), an end-to-end diffusion model that restores photo-realistic images directly from the sensor RAW data. While recent sRGB-domain diffusion methods achieve impressive results, they are caught in a dilemma between high fidelity and image generation. These models process lossy sRGB inputs and neglect the accessibility of the sensor RAW images in many scenarios, e.g., in image and video capturing in edge devices, resulting in sub-optimal performance. RDDM obviates this limitation by directly restoring images in the RAW domain, replacing the conventional two-stage image signal processing (ISP)->Image Restoration (IR) pipeline. However, a simple adaptation of pre-trained diffusion models to the RAW domain confronts many challenges. To this end, we propose: (1) a RAW-domain VAE (RVAE), encoding sensor RAW and decoding it into an enhanced linear domain image, to solve the out-of-distribution (OOD) issues between the different domain distributions; (2) a configurable multi-bayer (CMB) LoRA module, adapting diverse RAW Bayer patterns such as RGGB, BGGR, etc. To compensate for the deficiency in the dataset, we develop a scalable data synthesis pipeline synthesizing RAW LQ-HQ pairs from existing sRGB datasets for large-scale training. Extensive experiments demonstrate RDDM's superiority over state-of-the-art sRGB diffusion methods, yielding higher fidelity results with fewer artifacts. Codes will be publicly available at https://github.com/YanCHEN-fr/RDDM.
title RDDM: Practicing RAW Domain Diffusion Model for Real-world Image Restoration
topic Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.19154