High dynamic range (HDR) video reconstruction is attracting more and more attention due to the superior visual quality compared with those of low dynamic range (LDR) videos. The availability of LDR-HDR training pairs is essential for the HDR reconstruction quality. However, there are still no real LDR-HDR pairs for dynamic scenes due to the difficulty in capturing LDR-HDR frames simultaneously. In this work, we propose to utilize a staggered sensor to capture two alternate exposure images simultaneously, which are then fused into an HDR frame in both raw and sRGB domains. In this way, we build a large scale LDR-HDR video dataset with 85 scenes and each scene contains 60 frames. Based on this dataset, we further propose a Raw-HDRNet, which utilizes the raw LDR frames as inputs. We propose a pyramid flow-guided deformation convolution to align neighboring frames. Experimental results demonstrate that 1) the proposed dataset can improve the HDR reconstruction performance on real scenes for three benchmark networks; 2) Compared with sRGB inputs, utilizing raw inputs can further improve the reconstruction quality and our proposed Raw-HDRNet is a strong baseline for raw HDR reconstruction. Our dataset and code will be released after the acceptance of this paper.
Efficient HDR Reconstruction from Real-World Raw Images
School of Electrical and Information Engineering, Tianjin University（天津大学电气与信息工程学院）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；College of Intelligence and Computing, Tianjin University（天津大学智能与计算学院）；Shenzhen Bit Microelectronics Technology Co., Ltd（深圳比特微电子技术有限公司）
Color Matching Using Hypernetwork-Based Kolmogorov-Arnold Networks
Samara National Research University（萨马拉国立研究大学）；University of Würzburg（维尔茨堡大学）；York University（约克大学）；Institute for Information Transmission Problems RAS（俄罗斯科学院信息传输问题研究所）；Moscow Institute of Physics and Technologies（莫斯科物理技术学院）；Artificial Intelligence Research Institute（人工智能研究院）
本文提出 cmKAN 框架，利用超网络生成空间权重图控制 KAN 非线性样条，完成多种相机色彩空间下的颜色匹配，并构建大规模成对图像数据集，性能平均提升 37.3%。
High Dynamic Range Video Reconstruction from Single-Exposure Raw Sequences
Hangzhou Dianzi University（杭州电子科技大学）；Zhejiang Provincial Key Laboratory of Low Altitude Ubiquitous Networking Technology, Hangzhou Dianzi University（浙江省低空泛在组网技术重点实验室，杭州电子科技大学）；Institute of Microelectronics, Chinese Academy of Sciences（中国科学院微电子研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Beijing Institute of Technology（北京理工大学）
York University（约克大学）；Samsung AI Center – Toronto（三星人工智能中心多伦多分部）
Most camera images are rendered and saved in the standard RGB (sRGB) format by the camera's hardware. Due to the in-camera photo-finishing routines, nonlinear sRGB images are undesirable for computer vision tasks that assume a direct relationship between pixel values and scene radiance. For such applications, linear raw-RGB sensor images are preferred. Saving images in their raw-RGB format is still uncommon due to the large storage requirement and lack of support by many imaging applications. Several "raw reconstruction" methods have been proposed that utilize specialized metadata sampled from…
RAW image datasets are more suitable than the standard RGB image datasets for the ill-posed inverse problems in low-level vision, but not common in the literature. There are also a few studies to focus on mapping sRGB images to RAW format. Mapping from sRGB to RAW format could be a relevant domain for reverse style transferring since the task is an ill-posed reversing problem. In this study, we seek an answer to the question: Can the ISP operations be modeled as the style factor in an end-to-end learning pipeline? To investigate this idea, we propose a novel architecture, namely RST-ISP-Net, f…
Image recognition models that work in challenging environments (e.g., extremely dark, blurry, or high dynamic range conditions) must be useful. However, creating training datasets for such environments is expensive and hard due to the difficulties of data collection and annotation. It is desirable if we could get a robust model without the need for hard-to-obtain datasets. One simple approach is to apply data augmentation such as color jitter and blur to standard RGB (sRGB) images in simple scenes. Unfortunately, this approach struggles to yield realistic images in terms of pixel intensity and…
The Hong Kong University of Science and Technology（香港科技大学）
Unprocessed RAW data is a highly valuable image format for image editing and computer vision. However, since the file size of RAW data is huge, most users can only get access to processed and compressed sRGB images. To bridge this gap, we design an Invertible Image Signal Processing (InvISP) pipeline, which not only enables rendering visually appealing sRGB images but also allows recovering nearly perfect RAW data. Due to our framework's inherent reversibility, we can reconstruct realistic RAW data instead of synthesizing RAW data from sRGB images without any memory overhead. We also integrate…
York University（约克大学）；Vector Institute（向量研究所）；Samsung AI Center–Toronto（三星人工智能中心（多伦多））
Noise modeling and reduction are fundamental tasks in low-level computer vision. They are particularly important for smartphone cameras relying on small sensors that exhibit visually noticeable noise. There has recently been renewed interest in using data-driven approaches to improve camera noise models via neural networks. These data-driven approaches target noise present in the raw-sensor image before it has been processed by the camera's image signal processor (ISP). Modeling noise in the RAW-rgb domain is useful for improving and testing the in-camera denoising algorithm; however, there ar…
Learning Arbitrary-Scale RAW Image Downscaling with Wavelet-based Recurrent Reconstruction
School of Aeronautics and Astronautics, Sichuan University（四川大学航空宇航学院）；Xiaomi Inc.（小米公司）；University of Electronic Science and Technology of China（电子科技大学）
The Chinese University of Hong Kong（香港中文大学）；SmartMore（思谋科技）；Sensetime Research（商汤科技研究院）；Tetras AI（Tetras人工智能）
To facilitate video denoising research, we construct a compelling dataset, namely, "Practical Video Denoising Dataset" (PVDD), containing 200 noisy-clean dynamic video pairs in both sRGB and RAW format. Compared with existing datasets consisting of limited motion information, PVDD covers dynamic scenes with varying and natural motion. Different from datasets using primarily Gaussian or Poisson distributions to synthesize noise in the sRGB domain, PVDD synthesizes realistic noise from the RAW domain with a physically meaningful sensor noise model followed by ISP processing. Moreover, we also pr…
Visual Autoregressive Priors for RAW-to-sRGB Image Signal Processing
OmniVision-IDT Joint Laboratory for Intelligent Image Sensing（豪威科技-东方理工智能图像感知联合实验室）；Ningbo Key Laboratory of Spatial Intelligence and Digital Derivative（宁波市空间智能与数字衍生重点实验室）；Ningbo Institute of Digital Twin, Eastern Institute of Technology, Ningbo（宁波东方理工数字孪生研究院）；Zhejiang Key Laboratory of Industrial Intelligence and Digital Twin（浙江省工业智能与数字孪生重点实验室）；The Hong Kong Polytechnic University（香港理工大学）
Nanyang Technological University（南洋理工大学）；Peng Cheng Lab（鹏城实验室）；The Hong Kong Polytechnic University（香港理工大学）
While raw images exhibit advantages over sRGB images (e.g., linearity and fine-grained quantization level), they are not widely used by common users due to the large storage requirements. Very recent works propose to compress raw images by designing the sampling masks in the raw image pixel space, leading to suboptimal image representations and redundant metadata. In this paper, we propose a novel framework to learn a compact representation in the latent space serving as the metadata in an end-to-end manner. Furthermore, we propose a novel sRGB-guided context model with improved entropy estima…
In recent years, real image super-resolution (SR) has achieved promising results due to the development of SR datasets and corresponding real SR methods. In contrast, the field of real video SR is lagging behind, especially for real raw videos. Considering the superiority of raw image SR over sRGB image SR, we construct a real-world raw video SR (Real-RawVSR) dataset and propose a corresponding SR method. We utilize two DSLR cameras and a beam-splitter to simultaneously capture low-resolution (LR) and high-resolution (HR) raw videos with 2x, 3x, and 4x magnifications. There are 450 video pairs…
We propose a patch-based method for the simultaneous denoising and fusion of a sequence of RAW multi-exposed images. A spatio-temporal criterion is used to select similar patches along the sequence, and a weighted principal component analysis permits to both denoise and fuse the multi exposed data. The overall strategy permits to denoise and fuse the set of images without the need of recovering each denoised image in the multi-exposure set, leading to a very efficient procedure. Several experiments show that the proposed method permits to obtain state-of-the-art fusion results with real RAW da…
In this paper, we make the first benchmark effort to elaborate on the superiority of using RAW images in the low light enhancement and develop a novel alternative route to utilize RAW images in a more flexible and practical way. Inspired by a full consideration on the typical image processing pipeline, we are inspired to develop a new evaluation framework, Factorized Enhancement Model (FEM), which decomposes the properties of RAW images into measurable factors and provides a tool for exploring how properties of RAW images affect the enhancement performance empirically. The empirical benchmark …
ETH Zürich（苏黎世联邦理工学院）；University of Würzburg（维尔茨堡大学）；KU Leuven（鲁汶大学）
We propose a trainable Image Signal Processing (ISP) framework that produces DSLR quality images given RAW images captured by a smartphone. To address the color misalignments between training image pairs, we employ a color-conditional ISP network and optimize a novel parametric color mapping between each input RAW and reference DSLR image. During inference, we predict the target color image by designing a color prediction network with efficient Global Context Transformer modules. The latter effectively leverage global information to learn consistent color and tone mappings. We further propose …
Efficient RAW Image Deblurring with Adaptive Frequency Modulation
School of Mathematics, Tianjin University（天津大学数学学院）；School of Computer Science and Technology, Harbin Institute of Technology（哈尔滨工业大学计算机科学与技术学院）；College of Intelligence and Computing, Tianjin University（天津大学智能与计算学院）
Deep learning-based blind image deblurring plays an essential role in solving image blur since all existing kernels are limited in modeling the real world blur. Thus far, researchers focus on powerful models to handle the deblurring problem and achieve decent results. For this work, in a new aspect, we discover the great opportunity for image enhancement (e.g., deblurring) directly from RAW images and investigate novel neural network structures benefiting RAW-based learning. However, to the best of our knowledge, there is no available RAW image deblurring dataset. Therefore, we built a new dat…
High dynamic range (HDR) imaging combines multiple images with different exposure times into a single high-quality image. The image signal processing pipeline (ISP) is a core component in digital cameras to perform these operations. It includes demosaicing of raw color filter array (CFA) data at different exposure times, alignment of the exposures, conversion to HDR domain, and exposure merging into an HDR image. Traditionally, such pipelines cascade algorithms that address these individual subtasks. However, cascaded designs suffer from error propagation, since simply combining multiple steps…
In recent years, the supervised learning strategy for real noisy image denoising has been emerging and has achieved promising results. In contrast, realistic noise removal for raw noisy videos is rarely studied due to the lack of noisy-clean pairs for dynamic scenes. Clean video frames for dynamic scenes cannot be captured with a long-exposure shutter or averaging multi-shots as was done for static images. In this paper, we solve this problem by creating motions for controllable objects, such as toys, and capturing each static moment for multiple times to generate clean video frames. In this w…
The limited dynamic range of commercial compact camera sensors results in an inaccurate representation of scenes with varying illumination conditions, adversely affecting image quality and subsequently limiting the performance of underlying image processing algorithms. Current state-of-the-art (SoTA) convolutional neural networks (CNN) are developed as post-processing techniques to independently recover under-/over-exposed images. However, when applied to images containing real-world degradations such as glare, high-beam, color bleeding with varying noise intensity, these algorithms amplify th…
Retinex-RAWMamba: Bridging Demosaicing and Denoising for Low-Light RAW Image Enhancement
Institute of Advanced Technology, University of Science and Technology of China（科学技术大学先进技术研究院）；School of Computer and Artificial Intelligence, Beijing Technology and Business University（北京科技与商务大学计算机与人工智能学院）；Institute of Artificial Intelligence, Hefei Comprehensive National Science Center（合肥综合性国家科学中心人工智能研究院）；University of Science and Technology of China（科学技术大学）；School of Automation, Northwestern Polytechnical University（西北工业大学自动化学院）
Neural Radiance Fields (NeRF) is a technique for high quality novel view synthesis from a collection of posed input images. Like most view synthesis methods, NeRF uses tonemapped low dynamic range (LDR) as input; these images have been processed by a lossy camera pipeline that smooths detail, clips highlights, and distorts the simple noise distribution of raw sensor data. We modify NeRF to instead train directly on linear raw images, preserving the scene's full dynamic range. By rendering raw output images from the resulting NeRF, we can perform novel high dynamic range (HDR) view synthesis ta…
