The choice of a loss function is an important factor when training neural networks for image restoration problems, such as single image super resolution. The loss function should encourage natural and perceptually pleasing results. A popular choice for a loss is a pre-trained network, such as VGG, which is used as a feature extractor for computing the difference between restored and reference images. However, such an approach has multiple drawbacks: it is computationally expensive, requires regularization and hyper-parameter tuning, and involves a large network trained on an unrelated task. Furthermore, it has been observed that there is no single loss function that works best across all applications and across different datasets. In this work, we instead propose to train a set of loss functions that are application specific in nature. Our loss function comprises a series of discriminators that are trained to detect and penalize the presence of application-specific artifacts. We show that a single natural image and corresponding distortions are sufficient to train our feature extractor that outperforms state-of-the-art loss functions in applications like single image super resolution, denoising, and JPEG artifact removal. Finally, we conclude that an effective loss function does not have to be a good predictor of perceived image quality, but instead needs to be specialized in identifying the distortions for a given restoration method.
Liaoning University of Technology（辽宁工业大学）；Dalian University（大连大学）
The proposal of perceptual loss solves the problem that per-pixel difference loss function causes the reconstructed image to be overly-smooth, which acquires a significant progress in the field of single image super-resolution reconstruction. Furthermore, the generative adversarial networks (GAN) is applied to the super-resolution field, which effectively improves the visual quality of the reconstructed image. However, under the condtion of high upscaling factors, the excessive abnormal reasoning of the network produces some distorted structures, so that there is a certain deviation between th…
Palo Alto High School（帕洛阿尔托高中）；Monta Vista High School（蒙塔维斯塔高中）；Saint Francis High School（圣弗朗西斯高中）；Stanford University（斯坦福大学）；University of California San Diego（加利福尼亚大学圣迭戈分校）
Lossy image compression has been studied extensively in the context of typical loss functions such as RMSE, MS-SSIM, etc. However, compression at low bitrates generally produces unsatisfying results. Furthermore, the availability of massive public image datasets appears to have hardly been exploited in image compression. Here, we present a paradigm for eliciting human image reconstruction in order to perform lossy image compression. In this paradigm, one human describes images to a second human, whose task is to reconstruct the target image using publicly available images and text instructions…
Single image super-resolution (SISR) is the task of inferring a high-resolution image from a single low-resolution image. Recent research on super-resolution has achieved great progress due to the development of deep convolutional neural networks in the field of computer vision. Existing super-resolution reconstruction methods have high performances in the criterion of Mean Square Error (MSE) but most methods fail to reconstruct an image with shape edges. To solve this problem, the mixed gradient error, which is composed by MSE and a weighted mean gradient error, is proposed in this work and a…
South China University of Technology（华南理工大学）；University of Texas at Arlington（德克萨斯大学阿灵顿分校）；Tencent AI Lab（腾讯人工智能实验室）
Deep neural networks have exhibited promising performance in image super-resolution (SR) due to the power in learning the non-linear mapping from low-resolution (LR) images to high-resolution (HR) images. However, most deep learning methods employ feed-forward architectures, and thus the dependencies between LR and HR images are not fully exploited, leading to limited learning performance. Moreover, most deep learning based SR methods apply the pixel-wise reconstruction error as the loss, which, however, may fail to capture high-frequency information and produce perceptually unsatisfying resul…
ETH Zurich（苏黎世联邦理工学院）；Google Research, Brain Team（谷歌研究院（大脑团队））
We leverage the powerful lossy image compression algorithm BPG to build a lossless image compression system. Specifically, the original image is first decomposed into the lossy reconstruction obtained after compressing it with BPG and the corresponding residual. We then model the distribution of the residual with a convolutional neural network-based probabilistic model that is conditioned on the BPG reconstruction, and combine it with entropy coding to losslessly encode the residual. Finally, the image is stored using the concatenation of the bitstreams produced by BPG and the learned residual…
Compression of hyperspectral images onboard of spacecrafts is a tradeoff between the limited computational resources and the ever-growing spatial and spectral resolution of the optical instruments. As such, it requires low-complexity algorithms with good rate-distortion performance and high throughput. In recent years, the Consultative Committee for Space Data Systems (CCSDS) has focused on lossless and near-lossless compression approaches based on predictive coding, resulting in the recently published CCSDS 123.0-B-2 recommended standard. While the in-loop reconstruction of quantized predicti…
Indian Institute of Technology Roorkee（印度理工学院鲁尔基分校）；Indian Statistical Institute Calcutta（印度统计研究所加尔各答分所）
Haze and fog reduce the visibility of outdoor scenes as a veil like semi-transparent layer appears over the objects. As a result, images captured under such conditions lack contrast. Image dehazing methods try to alleviate this problem by recovering a clear version of the image. In this paper, we propose a Fully Convolutional Neural Network based model to recover the clear scene radiance by estimating the environmental illumination and the scene transmittance jointly from a hazy image. The method uses a relaxed haze imaging model to allow for the situations with non-uniform illumination. We ha…
Anyvision（安视维）；Queen’s University Belfast（贝尔法斯特女王大学）
Despite the breakthroughs in quality of image enhancement, an end-to-end solution for simultaneous recovery of the finer texture details and sharpness for degraded images with low resolution is still unsolved. Some existing approaches focus on minimizing the pixel-wise reconstruction error which results in a high peak signal-to-noise ratio. The enhanced images fail to provide high-frequency details and are perceptually unsatisfying, i.e., they fail to match the quality expected in a photo-realistic image. In this paper, we present Image Enhancement Generative Adversarial Network (IEGAN), a ver…
Hanbat National University（韩巴大学）；Lunit Inc（Lunit公司）
To train the change detector, bi-temporal images taken at different times in the same area are used. However, collecting labeled bi-temporal images is expensive and time consuming. To solve this problem, various unsupervised change detection methods have been proposed, but they still require unlabeled bi-temporal images. In this paper, we propose unsupervised change detection based on image reconstruction loss using only unlabeled single temporal single image. The image reconstruction model is trained to reconstruct the original source image by receiving the source image and the photometricall…
The Athenian School（雅典纳中学）；Cornell University（康奈尔大学）
Because of the necessity to obtain high-quality images with minimal radiation doses, such as in low-field magnetic resonance imaging, super-resolution reconstruction in medical imaging has become more popular (MRI). However, due to the complexity and high aesthetic requirements of medical imaging, image super-resolution reconstruction remains a difficult challenge. In this paper, we offer a deep learning-based strategy for reconstructing medical images from low resolutions utilizing Transformer and Generative Adversarial Networks (T-GAN). The integrated system can extract more precise texture …
Image reconstruction and synthesis have witnessed remarkable progress thanks to the development of generative models. Nonetheless, gaps could still exist between the real and generated images, especially in the frequency domain. In this study, we show that narrowing gaps in the frequency domain can ameliorate image reconstruction and synthesis quality further. We propose a novel focal frequency loss, which allows a model to adaptively focus on frequency components that are hard to synthesize by down-weighting the easy ones. This objective function is complementary to existing spatial losses, o…
University of California at Berkeley（加州大学伯克利分校）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）；GE Global Research（通用电气全球研究院）；International Computer Science Institute（国际计算机科学研究所）
Purpose: To improve reconstruction fidelity of fine structures and textures in deep learning (DL) based reconstructions. Methods: A novel patch-based Unsupervised Feature Loss (UFLoss) is proposed and incorporated into the training of DL-based reconstruction frameworks in order to preserve perceptual similarity and high-order statistics. The UFLoss provides instance-level discrimination by mapping similar instances to similar low-dimensional feature vectors and is trained without any human annotation. By adding an additional loss function on the low-dimensional feature space during training, t…
Open Stream, Inc.（Open Stream公司）；Nippon Telegraph And Telephone East Corporation（东日本电信电话株式会社）
In image anomaly detection, Autoencoders are the popular methods that reconstruct the input image that might contain anomalies and output a clean image with no abnormalities. These Autoencoder-based methods usually calculate the anomaly score from the reconstruction error, the difference between the input image and the reconstructed image. On the other hand, the accuracy of the reconstruction is insufficient in many of these methods, so it leads to degraded accuracy of anomaly detection. To improve the accuracy of the reconstruction, we consider defining loss function in the frequency domain. …
University of Amsterdam（阿姆斯特丹大学）；DUniversum（3DUniversum）；Google Research（谷歌研究院）
In this paper we address the benefit of adding adversarial training to the task of monocular depth estimation. A model can be trained in a self-supervised setting on stereo pairs of images, where depth (disparities) are an intermediate result in a right-to-left image reconstruction pipeline. For the quality of the image reconstruction and disparity prediction, a combination of different losses is used, including L1 image reconstruction losses and left-right disparity smoothness. These are local pixel-wise losses, while depth prediction requires global consistency. Therefore, we extend the self…
University of Cambridge（剑桥大学）；Rice University（莱斯大学）
The Magnetic Resonance Imaging (MRI) processing chain starts with a critical acquisition stage that provides raw data for reconstruction of images for medical diagnosis. This flow usually includes a near-lossless data compression stage that enables digital storage and/or transmission in binary formats. In this work we propose a framework for joint optimization of the MRI reconstruction and lossy compression, producing compressed representations of medical images that achieve improved trade-offs between quality and bit-rate. Moreover, we demonstrate that lossy compression can even improve the r…
Applications that involve supervised training require paired images. Researchers of single image super-resolution (SISR) create such images by artificially generating blurry input images from the corresponding ground truth. Similarly we can create paired images with the canny edge. We propose Generator From Edges (GFE) [Figure 2]. Our aim is to determine the best architecture for GFE, along with reviews of perceptual loss [1, 2]. To this end, we conducted three experiments. First, we explored the effects of the adversarial loss often used in SISR. In particular, we uncovered that it is not an …
Institute of AI for Health, Helmholtz Munich – German Research Centre for Environmental Health（亥姆霍兹慕尼黑中心（德国环境健康研究中心）健康人工智能研究所）；Technical University of Munich（慕尼黑工业大学）
Reconstructing 3D objects from 2D images is both challenging for our brains and machine learning algorithms. To support this spatial reasoning task, contextual information about the overall shape of an object is critical. However, such information is not captured by established loss terms (e.g. Dice loss). We propose to complement geometrical shape information by including multi-scale topological features, such as connected components, cycles, and voids, in the reconstruction loss. Our method uses cubical complexes to calculate topological features of 3D volume data and employs an optimal tran…
Imperial College London（帝国理工学院）；University of Edinburgh（爱丁堡大学）；Hyperfine Research Inc.（Hyperfine研究公司）；University of Birmingham（伯明翰大学）；NIH Clinical Center（美国国立卫生研究院临床中心）
We present a deep network interpolation strategy for accelerated parallel MR image reconstruction. In particular, we examine the network interpolation in parameter space between a source model that is formulated in an unrolled scheme with L1 and SSIM losses and its counterpart that is trained with an adversarial loss. We show that by interpolating between the two different models of the same network structure, the new interpolated network can model a trade-off between perceptual quality and fidelity.
Research Center for Medical Big Data, National Institute of Informatics（日本情报学研究所医疗大数据研究中心）；LPixel Inc.（LPixel公司）；Graduate School of Information Science and Technology, The University of Tokyo（东京大学信息科学与技术研究生院）；Department of Radiology, University of Cambridge（剑桥大学放射科）；Cancer Research UK Cambridge Centre（英国癌症研究中心剑桥中心）；Department of Artificial Intelligence, ELTE Eötvös Loránd University（厄特沃什罗兰大学人工智能系）；Department of Rehabilitation Medicine, Juntendo University School of Medicine（顺天堂大学医学部康复医学科）；International Research Center for Neurointelligence (WPI-IRCN), The University of Tokyo（东京大学国际神经智能研究中心（WPI-IRCN））
Unsupervised learning can discover various unseen diseases, relying on large-scale unannotated medical images of healthy subjects. Towards this, unsupervised methods reconstruct a single medical image to detect outliers either in the learned feature space or from high reconstruction loss. However, without considering continuity between multiple adjacent slices, they cannot directly discriminate diseases composed of the accumulation of subtle anatomical anomalies, such as Alzheimer's Disease (AD). Moreover, no study has shown how unsupervised anomaly detection is associated with disease stages.…
Technion Israel Institute of Technology（以色列理工学院）；McGovern Institute for Brain Research, Massachusetts Institute of Technology（麻省理工学院麦戈文脑科学研究所）
Compressed sensing (CS) is a signal processing framework for efficiently reconstructing a signal from a small number of measurements, obtained by linear projections of the signal. In this paper we present an end-to-end deep learning approach for CS, in which a fully-connected network performs both the linear sensing and non-linear reconstruction stages. During the training phase, the sensing matrix and the non-linear reconstruction operator are jointly optimized using Structural similarity index (SSIM) as loss rather than the standard Mean Squared Error (MSE) loss. We compare the proposed appr…
Bangladesh University of Engineering and Technology（孟加拉国工程技术大学）
Parallel imaging accelerates MRI data acquisition by acquiring additional sensitivity information with an array of receiver coils, resulting in fewer phase encoding steps. Because of fewer data requirements than parallel imaging, compressed sensing magnetic resonance imaging (CS-MRI) has gained popularity in the field of medical imaging. Parallel imaging and compressed sensing (CS) both reduce the amount of data captured in the k-space, which speeds up traditional MRI acquisition. As acquisition time is inversely proportional to sample count, forming an image from reduced k-space samples resul…
Image Sciences Institute, University Medical Center Utrecht（乌得勒支大学医学中心影像科学研究所）；Department of Radiology, University Medical Center Utrecht（乌得勒支大学医学中心放射科）；Department of Neurology and Neurosurgery, UMC Utrecht Brain Center, University Medical Center Utrecht（乌得勒支大学医学中心神经病学与神经外科系，乌得勒支大学医学中心脑中心）
Time-of-Flight Magnetic Resonance Angiographs (TOF-MRAs) enable visualization and analysis of cerebral arteries. This analysis may indicate normal variation of the configuration of the cerebrovascular system or vessel abnormalities, such as aneurysms. A model would be useful to represent normal cerebrovascular structure and variabilities in a healthy population and to differentiate from abnormalities. Current anomaly detection using autoencoding convolutional neural networks usually use a voxelwise mean-error for optimization. We propose optimizing a variational-autoencoder (VAE) with structur…
University of Science and Technology of China（中国科学技术大学）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）
Existing deep learning based HDRTV reconstruction methods assume one kind of tone mapping operators (TMOs) as the degradation procedure to synthesize SDRTV-HDRTV pairs for supervised training. In this paper, we argue that, although traditional TMOs exploit efficient dynamic range compression priors, they have several drawbacks on modeling the realistic degradation: information over-preservation, color bias and possible artifacts, making the trained reconstruction networks hard to generalize well to real-world cases. To solve this problem, we propose a learning-based data synthesis approach to …
Image reconstruction using deep learning algorithms offers improved reconstruction quality and lower reconstruction time than classical compressed sensing and model-based algorithms. Unfortunately, clean and fully sampled ground-truth data to train the deep networks is often unavailable in several applications, restricting the applicability of the above methods. We introduce a novel metric termed the ENsemble Stein's Unbiased Risk Estimate (ENSURE) framework, which can be used to train deep image reconstruction algorithms without fully sampled and noise-free images. The proposed framework is t…
University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）
One of the key elements of reconstructing a 3D mesh from a monocular video is generating every frame's depth map. However, in the application of colonoscopy video reconstruction, producing good-quality depth estimation is challenging. Neural networks can be easily fooled by photometric distractions or fail to capture the complex shape of the colon surface, predicting defective shapes that result in broken meshes. Aiming to fundamentally improve the depth estimation quality for colonoscopy 3D reconstruction, in this work we have designed a set of training losses to deal with the special challen…
Microsoft Research（微软研究院）；University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；University of Minnesota（明尼苏达大学）；Stanford University（斯坦福大学）
Deep learning techniques have emerged as a promising approach to highly accelerated MRI. However, recent reconstruction challenges have shown several drawbacks in current deep learning approaches, including the loss of fine image details even using models that perform well in terms of global quality metrics. In this study, we propose an end-to-end deep learning framework for image reconstruction and pathology detection, which enables a clinically aware evaluation of deep learning reconstruction quality. The solution is demonstrated for a use case in detecting meniscal tears on knee MRI studies…
Circular Phase Representation and Geometry-Aware Optimization for Ptychographic Image Reconstruction
School of Electrical and Computer Engineering, University of Sydney（悉尼大学电气与计算机工程学院）；Department of Engineering and System Science, National Tsing Hua University（清华大学系统科学系）
VinAI Research（VinAI研究院）；University of California San Diego（加州大学圣地亚哥分校）
High dynamic range (HDR) imaging is an indispensable technique in modern photography. Traditional methods focus on HDR reconstruction from multiple images, solving the core problems of image alignment, fusion, and tone mapping, yet having a perfect solution due to ghosting and other visual artifacts in the reconstruction. Recent attempts at single-image HDR reconstruction show a promising alternative: by learning to map pixel values to their irradiance using a neural network, one can bypass the align-and-merge pipeline completely yet still obtain a high-quality HDR image. In this work, we prop…
This paper proposes an extension to the Dual Branch Prior-Net for sparse view interventional CBCT reconstruction incorporating a high quality planning scan. An additional head learns to segment interventional instruments and thus guides the reconstruction task. The prior scans are misaligned by up to +-5deg in-plane during training. Experiments show that the proposed model, Dual Branch Prior-SegNet, significantly outperforms any other evaluated model by >2.8dB PSNR. It also stays robust wrt. rotations of up to +-5.5deg.
Purpose: Many useful image quality metrics for evaluating linear image reconstruction techniques do not apply to or are difficult to interpret for non-linear image reconstruction. The vast majority of metrics employed for evaluating non-linear image reconstruction are based on some form of global image fidelity, such as image root mean square error (RMSE). Use of such metrics can lead to over-regularization in the sense that they can favor removal of subtle details in the image. To address this shortcoming, we develop an image quality metric based on signal detection that serves as a surrogate…
Digital cameras can only capture a limited range of real-world scenes' luminance, producing images with saturated pixels. Existing single image high dynamic range (HDR) reconstruction methods attempt to expand the range of luminance, but are not able to hallucinate plausible textures, producing results with artifacts in the saturated areas. In this paper, we present a novel learning-based approach to reconstruct an HDR image by recovering the saturated pixels of an input LDR image in a visually pleasing way. Previous deep learning-based methods apply the same convolutional filters on well-expo…
Compared with the conventional 1*1 acquisition mode of projection in computed tomography (CT) image reconstruction, the 2*2 acquisition mode improves the collection efficiency of the projection and reduces the X-ray exposure time. However, the collected projection based on the 2*2 acquisition mode has low resolution (LR) and the reconstructed image quality is poor, thus limiting the use of this mode in CT imaging systems. In this study, a novel sinogram-super-resolution generative adversarial network (SSR-GAN) model is proposed to obtain high-resolution (HR) sinograms from LR sinograms, thereb…
