RAW-to-sRGB mapping, or the simulation of the traditional camera image signal processor (ISP), aims to generate DSLR-quality sRGB images from raw data captured by smartphone sensors. Despite achieving comparable results to sophisticated handcrafted camera ISP solutions, existing learning-based methods still struggle with detail disparity and color distortion. In this paper, we present ISPDiffuser, a diffusion-based decoupled framework that separates the RAW-to-sRGB mapping into detail reconstruction in grayscale space and color consistency mapping from grayscale to sRGB. Specifically, we propose a texture-aware diffusion model that leverages the generative ability of diffusion models to focus on local detail recovery, in which a texture enrichment loss is further proposed to prompt the diffusion model to generate more intricate texture details. Subsequently, we introduce a histogram-guided color consistency module that utilizes color histogram as guidance to learn precise color information for grayscale to sRGB color consistency mapping, with a color consistency loss designed to constrain the learned color information. Extensive experimental results show that the proposed ISPDiffuser outperforms state-of-the-art competitors both quantitatively and visually.

Image downscaling is critical for efficient storage and transmission of high-resolution (HR) images. Existing learning-based methods focus on performing downscaling within the sRGB domain, which typically suffers from blurred details and unexpected artifacts. RAW images, with their unprocessed photonic information, offer greater flexibility but lack specialized downscaling frameworks. In this paper, we propose a wavelet-based recurrent reconstruction framework that leverages the information lossless attribute of wavelet transformation to fulfill the arbitrary-scale RAW image downscaling in a coarse-to-fine manner, in which the Low-Frequency Arbitrary-Scale Downscaling Module (LASDM) and the High-Frequency Prediction Module (HFPM) are proposed to preserve structural and textural integrity of the reconstructed low-resolution (LR) RAW images, alongside an energy-maximization loss to align high-frequency energy between HR and LR domain. Furthermore, we introduce the Realistic Non-Integer RAW Downscaling (Real-NIRD) dataset, featuring a non-integer downscaling factor of 1.3×, and incorporate it with publicly available datasets with integer factors (2×, 3×, 4×) for comprehensive benchmarking arbitrary-scale image downscaling purposes. Extensive experiments demonstrate that our method outperforms existing state-of-the-art competitors both quantitatively and visually. The code and dataset will be released at https://github.com/RenYangSCU/ASRD.

Learning contextual information has been proved to be conducive to reducing mismatches in ill-posed regions, and many data-driven stereo matching algorithms achieve state-of-the-art performances. Global contextual information is difficult to learn by a shallow convolutional neural network, while a large network brings huge computational cost. This paper proposes a self-attention framework of stereo matching to learn both global and local contextual information. From a rough estimation, the disparity can be extremely refined by applying the proposed attention module. We present two self-attention modes to better learn global and local context synchronously. Experimental results show the proposed algorithm can well predict thin structures, large occluded or textureless regions, and achieves the comparable performance to state-of-the-art methods on the public stereo benchmark with a real-time speed.

This paper aims to combine spatial and frequency information for single image deblurring. Although some methods have tried to use frequency information to perform deblurring, they only simply process the different frequencies information separately or concatenate the real part and imaginary part of frequency features but ignore the strong correlation between them. To address this problem, we propose a simple but effective frequency interaction pipeline to realize the mutual conversion of the real part and the imaginary part. Then, we construct a spatial-frequency conversion module (SFCM) to promote the mutual conversion between the frequency information and the spatial information. Based on the proposed components, we build a multi-scale deblurring network, dubbed SFDNet, which can fully exploit coarse and middle-level information in spatial and frequency domains for finer scale image deblurring. Extensive experiments on the GoPro and HIDE datasets demonstrate that the proposed network outperforms the state-of-the-art methods both quantitatively and visually.