RAWMamba: Unified sRGB-to-RAW De-rendering With State Space Model

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Chen, Hongjun, Han, Wencheng, Zheng, Huan, Shen, Jianbing
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929595710701568
author Chen, Hongjun
Han, Wencheng
Zheng, Huan
Shen, Jianbing
author_facet Chen, Hongjun
Han, Wencheng
Zheng, Huan
Shen, Jianbing
contents Recent advancements in sRGB-to-RAW de-rendering have increasingly emphasized metadata-driven approaches to reconstruct RAW data from sRGB images, supplemented by partial RAW information. In image-based de-rendering, metadata is commonly obtained through sampling, whereas in video tasks, it is typically derived from the initial frame. The distinct metadata requirements necessitate specialized network architectures, leading to architectural incompatibilities that increase deployment complexity. In this paper, we propose RAWMamba, a Mamba-based unified framework developed for sRGB-to-RAW de-rendering across both image and video domains. The core of RAWMamba is the Unified Metadata Embedding (UME) module, which harmonizes diverse metadata types into a unified representation. In detail, a multi-perspective affinity modeling method is proposed to promote the extraction of reference information. In addition, we introduce the Local Tone-Aware Mamba (LTA-Mamba) module, which captures long-range dependencies to enable effective global propagation of metadata. Experimental results demonstrate that the proposed RAWMamba achieves state-of-the-art performance, yielding high-quality RAW data reconstruction.
format Preprint
id arxiv_https___arxiv_org_abs_2411_11717
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle RAWMamba: Unified sRGB-to-RAW De-rendering With State Space Model
Chen, Hongjun
Han, Wencheng
Zheng, Huan
Shen, Jianbing
Computer Vision and Pattern Recognition
Recent advancements in sRGB-to-RAW de-rendering have increasingly emphasized metadata-driven approaches to reconstruct RAW data from sRGB images, supplemented by partial RAW information. In image-based de-rendering, metadata is commonly obtained through sampling, whereas in video tasks, it is typically derived from the initial frame. The distinct metadata requirements necessitate specialized network architectures, leading to architectural incompatibilities that increase deployment complexity. In this paper, we propose RAWMamba, a Mamba-based unified framework developed for sRGB-to-RAW de-rendering across both image and video domains. The core of RAWMamba is the Unified Metadata Embedding (UME) module, which harmonizes diverse metadata types into a unified representation. In detail, a multi-perspective affinity modeling method is proposed to promote the extraction of reference information. In addition, we introduce the Local Tone-Aware Mamba (LTA-Mamba) module, which captures long-range dependencies to enable effective global propagation of metadata. Experimental results demonstrate that the proposed RAWMamba achieves state-of-the-art performance, yielding high-quality RAW data reconstruction.
title RAWMamba: Unified sRGB-to-RAW De-rendering With State Space Model
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.11717