Cameras capture sensor RAW images and transform them into pleasant RGB images, suitable for the human eyes, using their integrated Image Signal Processor (ISP). Numerous low-level vision tasks operate in the RAW domain (e.g. image denoising, white balance) due to its linear relationship with the scene irradiance, wide-range of information at 12bits, and sensor designs. Despite this, RAW image datasets are scarce and more expensive to collect than the already large and public RGB datasets.
This paper introduces the AIM 2022 Challenge on Reversed Image Signal Processing and RAW Reconstruction. We aim to recover raw sensor images from the corresponding RGBs without metadata and, by doing this, "reverse" the ISP transformation. The proposed methods and benchmark establish the state-of-the-art for this low-level vision inverse problem, and generating realistic raw sensor readings can potentially benefit other tasks such as denoising and super-resolution.
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…
Unprocessed sensor outputs (RAW images) potentially improve both low-level and high-level computer vision algorithms, but the lack of large-scale RAW image datasets is a barrier to research. Thus, reversed Image Signal Processing (ISP) which converts existing RGB images into RAW images has been studied. However, most existing methods require camera-specific metadata or paired RGB and RAW images to model the conversion, and they are not always available. In addition, there are issues in handling diverse ISPs and recovering global illumination. To tackle these limitations, we propose a self-supe…
McMaster University（麦克马斯特大学）；University of Waterloo（滑铁卢大学）
To the best of our knowledge, the existing deep-learning-based Video Super-Resolution (VSR) methods exclusively make use of videos produced by the Image Signal Processor (ISP) of the camera system as inputs. Such methods are 1) inherently suboptimal due to information loss incurred by non-invertible operations in ISP, and 2) inconsistent with the real imaging pipeline where VSR in fact serves as a pre-processing unit of ISP. To address this issue, we propose a new VSR method that can directly exploit camera sensor data, accompanied by a carefully built Raw Video Dataset (RawVD) for training, v…
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…
The lack of large-scale real raw image denoising dataset gives rise to challenges on synthesizing realistic raw image noise for training denoising models. However, the real raw image noise is contributed by many noise sources and varies greatly among different sensors. Existing methods are unable to model all noise sources accurately, and building a noise model for each sensor is also laborious. In this paper, we introduce a new perspective to synthesize noise by directly sampling from the sensor's real noise. It inherently generates accurate raw image noise for different camera sensors. Two e…
Zhejiang University（浙江大学）；Kunming Cotech Communication & Information Systems Co., Ltd（昆明科泰通信信息系统有限公司）
A lensless camera is an imaging system that uses a mask in place of a lens, making it thinner, lighter, and less expensive than a lensed camera. However, additional complex computation and time are required for image reconstruction. This work proposes a deep learning model named Raw3dNet that recognizes hand gestures directly on raw videos captured by a lensless camera without the need for image restoration. In addition to conserving computational resources, the reconstruction-free method provides privacy protection. Raw3dNet is a novel end-to-end deep neural network model for the recognition …
Under-display cameras have been proposed in recent years as a way to reduce the form factor of mobile devices while maximizing the screen area. Unfortunately, placing the camera behind the screen results in significant image distortions, including loss of contrast, blur, noise, color shift, scattering artifacts, and reduced light sensitivity. In this paper, we propose an image-restoration pipeline that is ISP-agnostic, i.e. it can be combined with any legacy ISP to produce a final image that matches the appearance of regular cameras using the same ISP. This is achieved with a deep learning app…
Inria（法国国家信息与自动化研究所）；DI/ENS (ENS-PSL, CNRS, Inria)（巴黎高等师范学院计算机系（巴黎文理研究大学巴黎高师、法国国家科学研究中心、法国国家信息与自动化研究所））；Université Paris-Saclay（巴黎萨克雷大学）；ENS Paris-Saclay（巴黎-萨克雷高等师范学院）；Centre Borelli（博雷利中心）；Center for Data Science, New York University（纽约大学数据科学中心）；Univ. Grenoble Alpes（格勒诺布尔阿尔卑斯大学）；CNRS（法国国家科学研究中心）；Grenoble INP（格勒诺布尔理工学院）；LJK（让·昆茨曼实验室）
Photographs captured by smartphones and mid-range cameras have limited spatial resolution and dynamic range, with noisy response in underexposed regions and color artefacts in saturated areas. This paper introduces the first approach (to the best of our knowledge) to the reconstruction of high-resolution, high-dynamic range color images from raw photographic bursts captured by a handheld camera with exposure bracketing. This method uses a physically-accurate model of image formation to combine an iterative optimization algorithm for solving the corresponding inverse problem with a learned imag…
Digital cameras transform sensor RAW readings into RGB images by means of their Image Signal Processor (ISP). Computational photography tasks such as image denoising and colour constancy are commonly performed in the RAW domain, in part due to the inherent hardware design, but also due to the appealing simplicity of noise statistics that result from the direct sensor readings. Despite this, the availability of RAW images is limited in comparison with the abundance and diversity of available RGB data. Recent approaches have attempted to bridge this gap by estimating the RGB to RAW mapping: hand…
With the advent of deep learning methods replacing the ISP in transforming sensor RAW readings into RGB images, numerous methodologies solidified into real-life applications. Equally potent is the task of inverting this process which will have applications in enhancing computational photography tasks that are conducted in the RAW domain, addressing lack of available RAW data while reaping from the benefits of performing tasks directly on sensor readings. This paper's proposed methodology is a state-of-the-art solution to the task of RAW reconstruction, and the multi-step refinement process int…
RAWIC: Bit-Depth Adaptive Lossless Raw Image Compression
School of Electronics, Peking University（北京大学电子学院）；Institute for AI Industry Research (AIR), Tsinghua University（清华大学人工智能产业研究院）；University of Chinese Academy of Sciences（中国科学院大学）
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…
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）
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）
Quantitative susceptibility mapping (QSM) is a valuable MRI post-processing technique that quantifies the magnetic susceptibility of body tissue from phase data. However, the traditional QSM reconstruction pipeline involves multiple non-trivial steps, including phase unwrapping, background field removal, and dipole inversion. These intermediate steps not only increase the reconstruction time but amplify noise and errors. This study develops a large-stencil Laplacian preprocessed deep learning-based neural network for near instant quantitative field and susceptibility mapping (i.e., iQFM and iQ…
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…
Data-Efficient Networks for Multi-Contrast MRI Reconstruction based on a Generalized Content/Style Prior
Leiden University Medical Center（莱顿大学医学中心）；Philips Innovative Technologies（飞利浦创新技术公司）；Philips Cardiologs（飞利浦Cardiologs公司）；Eindhoven University of Technology（埃因霍温理工大学）
A novel deep learning-based magnetic resonance imaging reconstruction pipeline was designed to address fundamental image quality limitations of conventional reconstruction to provide high-resolution, low-noise MR images. This pipeline's unique aims were to convert truncation artifact into improved image sharpness while jointly denoising images to improve image quality. This new approach, now commercially available at AIR Recon DL (GE Healthcare, Waukesha, WI), includes a deep convolutional neural network (CNN) to aid in the reconstruction of raw data, ultimately producing clean, sharp images. …
The Hong Kong Polytechnic University（香港理工大学）；DAMO Academy, Alibaba Group（阿里巴巴集团达摩院）
Denoising and demosaicking are two essential steps to reconstruct a clean full-color image from the raw data. Recently, joint denoising and demosaicking (JDD) for burst images, namely JDD-B, has attracted much attention by using multiple raw images captured in a short time to reconstruct a single high-quality image. One key challenge of JDD-B lies in the robust alignment of image frames. State-of-the-art alignment methods in feature domain cannot effectively utilize the temporal information of burst images, where large shifts commonly exist due to camera and object motion. In addition, the hig…
We propose the first accurate digitization and color reconstruction process for historical lenticular film that is robust to artifacts. Lenticular films emerged in the 1920s and were one of the first technologies that permitted to capture full color information in motion. The technology leverages an RGB filter and cylindrical lenticules embossed on the film surface to encode the color in the horizontal spatial dimension of the image. To project the pictures the encoding process was reversed using an appropriate analog device. In this work, we introduce an automated, fully digital pipeline to p…
Korea Advanced Institute of Science and Technology（韩国科学技术院）；Amazon Web Services（亚马逊云服务）
Reconstructing RGB image from RAW data obtained with a mobile device is related to a number of image signal processing (ISP) tasks, such as demosaicing, denoising, etc. Deep neural networks have shown promising results over hand-crafted ISP algorithms on solving these tasks separately, or even replacing the whole reconstruction process with one model. Here, we propose PyNET-CA, an end-to-end mobile ISP deep learning algorithm for RAW to RGB reconstruction. The model enhances PyNET, a recently proposed state-of-the-art model for mobile ISP, and improve its performance with channel attention and…
ShanghaiTech University（上海科技大学）；Chinese Academy of Sciences（中国科学院）；University of Chinese Academy of Sciences（中国科学院大学）
Photoacoustic imaging (PAI) is an emerging non-invasive imaging modality combining the advantages of deep ultrasound penetration and high optical contrast. Image reconstruction is an essential topic in PAI, which is unfortunately an ill-posed problem due to the complex and unknown optical/acoustic parameters in tissue. Conventional algorithms used in PAI (e.g., delay-and-sum) provide a fast solution while many artifacts remain, especially for linear array probe with limited-view issue. Convolutional neural network (CNN) has shown state-of-the-art results in computer vision, and more and more w…
ShanghaiTech University（上海科技大学）；Chinese Academy of Sciences（中国科学院）；Shanghai Institute of Microsystem and Information Technology（上海微系统与信息技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Photoacoustic (PA) imaging is a biomedical imaging modality capable of acquiring high-contrast images of optical absorption at depths much greater than traditional optical imaging techniques. However, practical instrumentation and geometry limit the number of available acoustic sensors surrounding the imaging target, which results in the sparsity of sensor data. Conventional PA image reconstruction methods give severe artifacts when they are applied directly to the sparse PA data. In this paper, we firstly propose to employ a novel signal processing method to make sparse PA raw data more suita…
We demonstrate that image reconstruction can be achieved via a convolutional neural network for a "see-through" computational camera comprised of a transparent window and a CMOS image sensor. Furthermore, we compared classification results using a classifier network for the raw sensor data vs the reconstructed images. The results suggest that similar classification accuracy is likely possible in both cases with appropriate network optimizations. All networks were trained and tested for the MNIST (6 classes), EMNIST and the Kanji49 datasets.
Environmental-induced temperature variations across the bridge deck were one of the major factors that degraded the performance of delamination detection through thermography. The non-uniformly distributed thermal background yields the assumption of most conventional quantitative methods used in practice such as global thresholding and k-means clustering. This study proposed a pre-processing method to estimate the thermal background through iterative grayscale morphologic reconstruction based on a pre-selected temperature contrast. After the estimation of the background, the thermal feature of…
Zhejiang University（浙江大学）；Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）；First Hospital of Shanxi Medical University（山西医科大学第一医院）
Patlak model is widely used in 18F-FDG dynamic positron emission tomography (PET) imaging, where the estimated parametric images reveal important biochemical and physiology information. Because of better noise modeling and more information extracted from raw sinogram, direct Patlak reconstruction gains its popularity over the indirect approach which utilizes reconstructed dynamic PET images alone. As the prerequisite of direct Patlak methods, raw data from dynamic PET are rarely stored in clinics and difficult to obtain. In addition, the direct reconstruction is time-consuming due to the bottl…
Magnetic Particle Imaging (MPI) is an emerging medical imaging modality that images the spatial distribution of superparamagnetic iron oxide (SPIO) nanoparticles using their nonlinear response to applied magnetic fields. In standard x-space approach to MPI, the image is reconstructed by gridding the speed-compensated nanoparticle signal to the instantaneous position of the field free point (FFP). However, due to safety limits on the drive field, the field-of-view (FOV) needs to be covered by multiple relatively small partial field-of-views (pFOVs). The image of the entire FOV is then pieced to…
Real-time magnetic resonance imaging (RT-MRI) of human speech production is enabling significant advances in speech science, linguistics, bio-inspired speech technology development, and clinical applications. Easy access to RT-MRI is however limited, and comprehensive datasets with broad access are needed to catalyze research across numerous domains. The imaging of the rapidly moving articulators and dynamic airway shaping during speech demands high spatio-temporal resolution and robust reconstruction methods. Further, while reconstructed images have been published, to-date there is no open da…
Johns Hopkins University（约翰斯·霍普金斯大学）；University of Science and Technology of China（中国科学技术大学）
Magnetic Resonance (MR) image reconstruction from under-sampled acquisition promises faster scanning time. To this end, current State-of-The-Art (SoTA) approaches leverage deep neural networks and supervised training to learn a recovery model. While these approaches achieve impressive performances, the learned model can be fragile on unseen degradation, e.g. when given a different acceleration factor. These methods are also generally deterministic and provide a single solution to an ill-posed problem; as such, it can be difficult for practitioners to understand the reliability of the reconstru…
Breast CT provides image volumes with isotropic resolution in high contrast, enabling detection of small calcification (down to a few hundred microns in size) and subtle density differences. Since breast is sensitive to x-ray radiation, dose reduction of breast CT is an important topic, and for this purpose, few-view scanning is a main approach. In this article, we propose a Deep Efficient End-to-end Reconstruction (DEER) network for few-view breast CT image reconstruction. The major merits of our network include high dose efficiency, excellent image quality, and low model complexity. By the d…
Department of Computer Science University College London（伦敦大学学院计算机科学系（注：按要求提取到大学级别，此处“Department of Computer Science University College London”整体作为机构，中文翻译为“伦敦大学学院计算机科学系”））
Increasingly in medical imaging has emerged an issue surrounding the reconstruction of noisy images from raw measurement data. Where the forward problem is the generation of raw measurement data from a ground truth image, the inverse problem is the reconstruction of those images from the measurement data. In most cases with medical imaging, classical inverse Radon transforms, such as an inverse Fourier transform for MRI, work well for recovering clean images from the measured data. Unfortunately in the case of X-Ray CT, where undersampled data is very common, more than this is needed to resolv…
FastMRI Prostate: A Publicly Available, Biparametric MRI Dataset to Advance Machine Learning for Prostate Cancer Imaging
New York University Grossman School of Medicine（纽约大学格罗斯曼医学院）；Siemens Medical Solutions USA（美国西门子医疗解决方案公司）；Courant Institute of Mathematical Sciences, New York University（纽约大学柯朗数学科学研究所）
Purpose of this study was to evaluate the effect of a robust magnetic resonance reconstruction pipeline equipped with a deep convolutional neural network on the overall image quality, in terms of Gibbs artifact reduction, and SNR improvement. Sixteen (16) healthy volunteers enrolled in this study and were imaged at 3T. Representative images of each image series that were reconstructed through the pipeline that leverages a deep learning (DL) algorithm were retrospectively benchmarked against corresponding images reconstructed through a conventional pipeline. DL-reconstructed images showed signi…
Low-dose CT image reconstruction has been a popular research topic in recent years. A typical reconstruction method based on post-log measurements is called penalized weighted-least squares (PWLS). Due to the underlying limitations of the post-log statistical model, the PWLS reconstruction quality is often degraded in low-dose scans. This paper investigates a shifted-Poisson (SP) model based likelihood function that uses the pre-log raw measurements that better represents the measurement statistics, together with a data-driven regularizer exploiting a Union of Learned TRAnsforms (SPULTRA). Bot…
The University of Tennessee（田纳西大学）；Siemens Medical Solutions Inc.（西门子医疗解决方案公司）
Direct reconstruction of positron emission tomography (PET) data using deep neural networks is a growing field of research. Initial results are promising, but often the networks are complex, memory utilization inefficient, produce relatively small 2D image slices (e.g., 128x128), and low count rate reconstructions are of varying quality. This paper proposes FastPET, a novel direct reconstruction convolutional neural network that is architecturally simple, memory space efficient, works for non-trivial 3D image volumes and is capable of processing a wide spectrum of PET data including low-dose a…
