RAW-Flow: Advancing RGB-to-RAW Image Reconstruction with Deterministic Latent Flow Matching
This work addresses the domain-specific problem of camera image processing for photography and computer vision applications, offering an incremental improvement over existing methods.
The paper tackles the problem of reconstructing RAW images from RGB images, a challenging inverse task due to information loss, by proposing RAW-Flow, a generative framework using deterministic latent flow matching, which achieves state-of-the-art performance with improved detail and color accuracy.
RGB-to-RAW reconstruction, or the reverse modeling of a camera Image Signal Processing (ISP) pipeline, aims to recover high-fidelity RAW data from RGB images. Despite notable progress, existing learning-based methods typically treat this task as a direct regression objective and struggle with detail inconsistency and color deviation, due to the ill-posed nature of inverse ISP and the inherent information loss in quantized RGB images. To address these limitations, we pioneer a generative perspective by reformulating RGB-to-RAW reconstruction as a deterministic latent transport problem and introduce a novel framework named RAW-Flow, which leverages flow matching to learn a deterministic vector field in latent space, to effectively bridge the gap between RGB and RAW representations and enable accurate reconstruction of structural details and color information. To further enhance latent transport, we introduce a cross-scale context guidance module that injects hierarchical RGB features into the flow estimation process. Moreover, we design a dual-domain latent autoencoder with a feature alignment constraint to support the proposed latent transport framework, which jointly encodes RGB and RAW inputs while promoting stable training and high-fidelity reconstruction. Extensive experiments demonstrate that RAW-Flow outperforms state-of-the-art approaches both quantitatively and visually.