Learning GAN-based Foveated Reconstruction to Recover Perceptually Important Image Features
Università della Svizzera italiana（瑞士意大利语区大学）；West Pomeranian University of Technology（西波美拉尼亚工业大学）；University of Groningen（格罗宁根大学）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）
Luca Surace, Marek Wernikowski, Cara Tursun, Karol Myszkowski, Radosław Mantiuk, Piotr Didyk
A foveated image can be entirely reconstructed from a sparse set of samples distributed according to the retinal sensitivity of the human visual system, which rapidly decreases with increasing eccentricity. The use of Generative Adversarial Networks has recently been shown to be a promising solution for such a task, as they can successfully hallucinate missing image information. As in the case of other supervised learning approaches, the definition of the loss function and the training strategy heavily influence the quality of the output. In this work,we consider the problem of efficiently guiding the training of foveated reconstruction techniques such that they are more aware of the capabilities and limitations of the human visual system, and thus can reconstruct visually important image features. Our primary goal is to make the training procedure less sensitive to distortions that humans cannot detect and focus on penalizing perceptually important artifacts. Given the nature of GAN-based solutions, we focus on the sensitivity of human vision to hallucination in case of input samples with different densities. We propose psychophysical experiments, a dataset, and a procedure for training foveated image reconstruction. The proposed strategy renders the generator network flexible by penalizing only perceptually important deviations in the output. As a result, the method emphasized the recovery of perceptually important image features. We evaluated our strategy and compared it with alternative solutions by using a newly trained objective metric, a recent foveated video quality metric, and user experiments. Our evaluations revealed significant improvements in the perceived image reconstruction quality compared with the standard GAN-based training approach.
Dynamical Neuroscience（动态神经科学中心）；Institute for Collaborative Biotechnologies（协同生物技术研究所）；UC Santa Barbara（加州大学圣巴巴拉分校）；Electric and Computer Engineering（电气与计算机工程学院）；Psychological and Brain Sciences（心理与脑科学学院）
The problem of $\textit{visual metamerism}$ is defined as finding a family of perceptually indistinguishable, yet physically different images. In this paper, we propose our NeuroFovea metamer model, a foveated generative model that is based on a mixture of peripheral representations and style transfer forward-pass algorithms. Our gradient-descent free model is parametrized by a foveated VGG19 encoder-decoder which allows us to encode images in high dimensional space and interpolate between the content and texture information with adaptive instance normalization anywhere in the visual field. Ou…
Human visual sensitivity to spatial details declines towards the periphery. Novel image synthesis techniques, so-called foveated rendering, exploit this observation and reduce the spatial resolution of synthesized images for the periphery, avoiding the synthesis of high-spatial-frequency details that are costly to generate but not perceived by a viewer. However, contemporary techniques do not make a clear distinction between the range of spatial frequencies that must be reproduced and those that can be omitted. For a given eccentricity, there is a range of frequencies that are detectable but n…
Existing approaches towards single image dehazing including both model-based and learning-based heavily rely on the estimation of so-called transmission maps. Despite its conceptual simplicity, using transmission maps as an intermediate step often makes it more difficult to optimize the perceptual quality of reconstructed images. To overcome this weakness, we propose a direct deep learning approach toward image dehazing bypassing the step of transmission map estimation and facilitating end-to-end perceptual optimization. Our technical contributions are mainly three-fold. First, based on the an…
With the recent interest in virtual reality and augmented reality, there is a newfound demand for displays that can provide high resolution with a wide field of view (FOV). However, such displays incur significantly higher costs for rendering the larger number of pixels. This poses the challenge of rendering realistic real-time images that have a wide FOV and high resolution using limited computing resources. The human visual system does not need every pixel to be rendered at a uniformly high quality. Foveated rendering methods provide perceptually high-quality images while reducing computatio…
Generative adversarial networks (GANs) have enabled photorealistic image synthesis and editing. However, due to the high computational cost of large-scale generators (e.g., StyleGAN2), it usually takes seconds to see the results of a single edit on edge devices, prohibiting interactive user experience. In this paper, we take inspirations from modern rendering software and propose Anycost GAN for interactive natural image editing. We train the Anycost GAN to support elastic resolutions and channels for faster image generation at versatile speeds. Running subsets of the full generator produce ou…
Shanghai Jiao Tong University（上海交通大学）；New York University（纽约大学）；UNC Chapel Hill（北卡罗来纳大学教堂山分校）；Peng Cheng Laboratory（鹏城实验室）
Virtual Reality (VR) is becoming ubiquitous with the rise of consumer displays and commercial VR platforms. Such displays require low latency and high quality rendering of synthetic imagery with reduced compute overheads. Recent advances in neural rendering showed promise of unlocking new possibilities in 3D computer graphics via image-based representations of virtual or physical environments. Specifically, the neural radiance fields (NeRF) demonstrated that photo-realistic quality and continuous view changes of 3D scenes can be achieved without loss of view-dependent effects. While NeRF can s…
As a fundamental issue in lifelong learning, catastrophic forgetting is directly caused by inaccessible historical data; accordingly, if the data (information) were memorized perfectly, no forgetting should be expected. Motivated by that, we propose a GAN memory for lifelong learning, which is capable of remembering a stream of datasets via generative processes, with \emph{no} forgetting. Our GAN memory is based on recognizing that one can modulate the "style" of a GAN model to form perceptually-distant targeted generation. Accordingly, we propose to do sequential style modulations atop a well…
Semi-supervised methods of anomaly detection have seen substantial advancement in recent years. Of particular interest are applications of such methods to diverse, real-world anomaly detection problems where anomalous variations can vary from the visually obvious to the very subtle. In this work, we propose a novel fine-grained VAE-GAN architecture trained in a semi-supervised manner in order to detect both visually distinct and subtle anomalies. With the use of a residually connected dual-feature extractor, a fine-grained discriminator and a perceptual loss function, we are able to detect sub…
Despite excellent performance in image generation, Generative Adversarial Networks (GANs) are notorious for its requirements of enormous storage and intensive computation. As an awesome ''performance maker'', knowledge distillation is demonstrated to be particularly efficacious in exploring low-priced GANs. In this paper, we investigate the irreplaceability of teacher discriminator and present an inventive discriminator-cooperated distillation, abbreviated as DCD, towards refining better feature maps from the generator. In contrast to conventional pixel-to-pixel match methods in feature map di…
Recent work has shown generative adversarial networks (GANs) can generate highly realistic images, that are often indistinguishable (by humans) from real images. Most images so generated are not contained in the training dataset, suggesting potential for augmenting training sets with GAN-generated data. While this scenario is of particular relevance when there are limited data available, there is still the issue of training the GAN itself based on that limited data. To facilitate this, we leverage existing GAN models pretrained on large-scale datasets (like ImageNet) to introduce additional kn…
This paper introduces a novel approach to texture synthesis based on generative adversarial networks (GAN) (Goodfellow et al., 2014). We extend the structure of the input noise distribution by constructing tensors with different types of dimensions. We call this technique Periodic Spatial GAN (PSGAN). The PSGAN has several novel abilities which surpass the current state of the art in texture synthesis. First, we can learn multiple textures from datasets of one or more complex large images. Second, we show that the image generation with PSGANs has properties of a texture manifold: we can smooth…
MIT BCS（麻省理工学院脑与认知科学系）；MIT CSAIL（麻省理工学院计算机科学与人工智能实验室）；MIT KFG（麻省理工学院知识未来小组）
A large body of recent work has identified transformations in the latent spaces of generative adversarial networks (GANs) that consistently and interpretably transform generated images. But existing techniques for identifying these transformations rely on either a fixed vocabulary of pre-specified visual concepts, or on unsupervised disentanglement techniques whose alignment with human judgments about perceptual salience is unknown. This paper introduces a new method for building open-ended vocabularies of primitive visual concepts represented in a GAN's latent space. Our approach is built fro…
Los Alamos National Laboratory（洛斯阿拉莫斯国家实验室）；Descartes Labs, Inc（笛卡尔实验室公司）
In this work we demonstrate that generative adversarial networks (GANs) can be used to generate realistic pervasive changes in remote sensing imagery, even in an unpaired training setting. We investigate some transformation quality metrics based on deep embedding of the generated and real images which enable visualization and understanding of the training dynamics of the GAN, and may provide a useful measure in terms of quantifying how distinguishable the generated images are from real images. We also identify some artifacts introduced by the GAN in the generated images, which are likely to co…
This paper introduces a novel approach to in-painting where the identity of the object to remove or change is preserved and accounted for at inference time: Exemplar GANs (ExGANs). ExGANs are a type of conditional GAN that utilize exemplar information to produce high-quality, personalized in painting results. We propose using exemplar information in the form of a reference image of the region to in-paint, or a perceptual code describing that object. Unlike previous conditional GAN formulations, this extra information can be inserted at multiple points within the adversarial network, thus incre…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Center for Devices and Radiological Health, Food and Drug Administration（美国食品药品监督管理局设备与放射健康中心）
In recent years, generative adversarial networks (GANs) have gained tremendous popularity for potential applications in medical imaging, such as medical image synthesis, restoration, reconstruction, translation, as well as objective image quality assessment. Despite the impressive progress in generating high-resolution, perceptually realistic images, it is not clear if modern GANs reliably learn the statistics that are meaningful to a downstream medical imaging application. In this work, the ability of a state-of-the-art GAN to learn the statistics of canonical stochastic image models (SIMs) t…
Volume data is found in many important scientific and engineering applications. Rendering this data for visualization at high quality and interactive rates for demanding applications such as virtual reality is still not easily achievable even using professional-grade hardware. We introduce FoVolNet -- a method to significantly increase the performance of volume data visualization. We develop a cost-effective foveated rendering pipeline that sparsely samples a volume around a focal point and reconstructs the full-frame using a deep neural network. Foveated rendering is a technique that prioriti…
Adversarial examples are fabricated examples, indistinguishable from the original image that mislead neural networks and drastically lower their performance. Recently proposed AdvGAN, a GAN based approach, takes input image as a prior for generating adversaries to target a model. In this work, we show how latent features can serve as better priors than input images for adversary generation by proposing AdvGAN++, a version of AdvGAN that achieves higher attack rates than AdvGAN and at the same time generates perceptually realistic images on MNIST and CIFAR-10 datasets.
University of British Columbia（英属哥伦比亚大学）；Department of Statistics, University of British Columbia（英属哥伦比亚大学统计系）；Department of Electrical and Computer Engineering, University of British Columbia（英属哥伦比亚大学电气与计算机工程系）；School of Information and Communications Engineering, Xi’an Jiaotong University（西安交通大学信息与通信工程学院）
Recently, generative adversarial networks (GANs) can generate photo-realistic fake facial images which are perceptually indistinguishable from real face photos, promoting research on fake face detection. Though fake face forensics can achieve high detection accuracy, their anti-forensic counterparts are less investigated. Here we explore more \textit{imperceptible} and \textit{transferable} anti-forensics for fake face imagery detection based on adversarial attacks. Since facial and background regions are often smooth, even small perturbation could cause noticeable perceptual impairment in fak…
Norwegian University of Science and Technology（挪威科技大学）
In minimally invasive surgery, the use of tissue dissection tools causes smoke, which inevitably degrades the image quality. This could reduce the visibility of the operation field for surgeons and introduces errors for the computer vision algorithms used in surgical navigation systems. In this paper, we propose a novel approach for computational smoke removal using supervised image-to-image translation. We demonstrate that straightforward application of existing generative algorithms allows removing smoke but decreases image quality and introduces synthetic noise (grid-structure). Thus, we pr…
In this paper, we address the problem of face hallucination by proposing a novel multi-scale generative adversarial network (GAN) architecture optimized for face verification. First, we propose a multi-scale generator architecture for face hallucination with a high up-scaling ratio factor, which has multiple intermediate outputs at different resolutions. The intermediate outputs have the growing goal of synthesizing small to large images. Second, we incorporate a face verifier with the original GAN discriminator and propose a novel discriminator which learns to discriminate different identitie…
Recent advances in the design of convolutional neural network (CNN) have yielded significant improvements in the performance of image super-resolution (SR). The boost in performance can be attributed to the presence of residual or dense connections within the intermediate layers of these networks. The efficient combination of such connections can reduce the number of parameters drastically while maintaining the restoration quality. In this paper, we propose a scale recurrent SR architecture built upon units containing series of dense connections within a residual block (Residual Dense Blocks (…
An ongoing trend in generative modelling research has been to push sample resolutions higher whilst simultaneously reducing computational requirements for training and sampling. We aim to push this trend further via the combination of techniques - each component representing the current pinnacle of efficiency in their respective areas. These include vector-quantized GAN (VQ-GAN), a vector-quantization (VQ) model capable of high levels of lossy - but perceptually insignificant - compression; hourglass transformers, a highly scaleable self-attention model; and step-unrolled denoising autoencoder…
Designing face recognition systems that are capable of matching face images obtained in the thermal spectrum with those obtained in the visible spectrum is a challenging problem. In this work, we propose the use of semantic-guided generative adversarial network (SG-GAN) to automatically synthesize visible face images from their thermal counterparts. Specifically, semantic labels, extracted by a face parsing network, are used to compute a semantic loss function to regularize the adversarial network during training. These semantic cues denote high-level facial component information associated wi…
Automatic animation line art colorization is a challenging computer vision problem, since the information of the line art is highly sparse and abstracted and there exists a strict requirement for the color and style consistency between frames. Recently, a lot of Generative Adversarial Network (GAN) based image-to-image translation methods for single line art colorization have emerged. They can generate perceptually appealing results conditioned on line art images. However, these methods can not be adopted for the purpose of animation colorization because there is a lack of consideration of the…
Arizona State University（亚利桑那州立大学）；Washington University in St. Louis（圣路易斯华盛顿大学）；Mayo Clinic（梅奥诊所）
Real-world non-mydriatic retinal fundus photography is prone to artifacts, imperfections and low-quality when certain ocular or systemic co-morbidities exist. Artifacts may result in inaccuracy or ambiguity in clinical diagnoses. In this paper, we proposed a simple but effective end-to-end framework for enhancing poor-quality retinal fundus images. Leveraging the optimal transport theory, we proposed an unpaired image-to-image translation scheme for transporting low-quality images to their high-quality counterparts. We theoretically proved that a Generative Adversarial Networks (GAN) model wit…
University of Wisconsin - Madison（威斯康星大学麦迪逊分校）；Carnegie Mellon University（卡内基梅隆大学）
Generating smooth animations from a limited number of sequential observations has a number of applications in vision. For example, it can be used to increase number of frames per second, or generating a new trajectory only based on first and last frames, e.g. a motion of face emotions. Despite the discrete observed data (frames), the problem of generating a new trajectory is a continues problem. In addition, to be perceptually realistic, the domain of an image should not alter drastically through the trajectory of changes. In this paper, we propose a new framework, Warping Neural ODE, for gene…
University of New South Wales（新南威尔士大学）；School of Minerals and Energy Resources Engineering（矿物与能源资源工程学院）
Digital Rock Imaging is constrained by detector hardware, and a trade-off between the image field of view (FOV) and the image resolution must be made. This can be compensated for with super resolution (SR) techniques that take a wide FOV, low resolution (LR) image, and super resolve a high resolution (HR), high FOV image. The Enhanced Deep Super Resolution Generative Adversarial Network (EDSRGAN) is trained on the Deep Learning Digital Rock Super Resolution Dataset, a diverse compilation 12000 of raw and processed uCT images. The network shows comparable performance of 50% to 70% reduction in …
Despite the breakthroughs in accuracy and speed of single image super-resolution using faster and deeper convolutional neural networks, one central problem remains largely unsolved: how do we recover the finer texture details when we super-resolve at large upscaling factors? The behavior of optimization-based super-resolution methods is principally driven by the choice of the objective function. Recent work has largely focused on minimizing the mean squared reconstruction error. The resulting estimates have high peak signal-to-noise ratios, but they are often lacking high-frequency details and…
Adversarial Wear and Tear: Exploiting Natural Damage for Generating Physical-World Adversarial Examples
Department of Computer Science and Engineering, Kyung Hee University（计算机科学与工程系，庆熙大学）；Technical University of Munich（慕尼黑技术大学）；Seoul National University of Science and Technology（首尔科学理工大学）；G-LAMP NEXUS Institute, Kyung Hee University（G-LAMP NEXUS研究所，庆熙大学）
Synthesis and Perceptual Scaling of High Resolution Naturalistic Images Using Stable Diffusion
Department of Psychology, Humboldt-Universität zu Berlin（柏林洪堡大学心理学系）；Bernstein Center for Computational Neuroscience Berlin and Berlin Center for Advanced Neuroimaging, Charité Universitätsmedizin Berlin（柏林伯恩斯坦计算神经科学中心和柏林先进神经成像中心，查理医学院）；Max Planck Institute for Human Cognitive and Brain Sciences, Leipzig, Germany（马克斯·普朗克人类认知与脑科学研究所，莱比锡，德国）；Max Planck School of Cognition, Leipzig, Germany（马克斯·普朗克认知学校，莱比锡，德国）；Kavli Institute for Systems Neuroscience, Centre for Neural Computation, The Egil and Pauline Braathen and Fred Kavli Centre for Cortical Microcircuits, Jebsen Centre for Alzheimer’s Disease, Norwegian University of Science and Technology, Trondheim, Norway（凯斯琳系统神经科学研究所，神经计算中心，埃吉和保罗·布雷athen及弗雷德·卡维利微电路中心，朱贝森阿尔茨海默病中心，挪威科学与技术大学，特罗姆瑟，挪威）；Clinic of Neurology, Charité-Universitätsmedizin Berlin, Berlin, Germany（柏林查理医学院神经科诊所）；Berlin Center for Advanced Neuroimaging, Charité-Universitätsmedizin Berlin, Berlin, Germany（柏林先进神经成像中心，查理医学院）；Research Cluster of Excellence “Science of Intelligence”, Technische（卓越研究集群“智能科学”，技术）
