Generative adversarial network-based image super-resolution using perceptual content losses
Yonsei University（延世大学）
Manri Cheon, Jun-Hyuk Kim, Jun-Ho Choi, Jong-Seok Lee
备注：
To appear in ECCV 2018 workshop. Won the 2nd place for Region 1 in the PIRM Challenge on Perceptual Super Resolution at ECCV 2018. Github at https://github.com/manricheon/eusr-pcl-tf
In this paper, we propose a deep generative adversarial network for super-resolution considering the trade-off between perception and distortion. Based on good performance of a recently developed model for super-resolution, i.e., deep residual network using enhanced upscale modules (EUSR), the proposed model is trained to improve perceptual performance with only slight increase of distortion. For this purpose, together with the conventional content loss, i.e., reconstruction loss such as L1 or L2, we consider additional losses in the training phase, which are the discrete cosine transform coefficients loss and differential content loss. These consider perceptual part in the content loss, i.e., consideration of proper high frequency components is helpful for the trade-off problem in super-resolution. The experimental results show that our proposed model has good performance for both perception and distortion, and is effective in perceptual super-resolution applications.
Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University（西安交通大学人工智能与机器人研究所）
Image Inpainting is a task that aims to fill in missing regions of corrupted images with plausible contents. Recent inpainting methods have introduced perceptual and style losses as auxiliary losses to guide the learning of inpainting generators. Perceptual and style losses help improve the perceptual quality of inpainted results by supervising deep features of generated regions. However, two challenges have emerged with the usage of auxiliary losses: (i) the time-consuming grid search is required to decide weights for perceptual and style losses to properly perform, and (ii) loss terms with d…
Recent approaches in generative adversarial networks (GANs) can automatically synthesize realistic images from descriptive text. Despite the overall fair quality, the generated images often expose visible flaws that lack structural definition for an object of interest. In this paper, we aim to extend state of the art for GAN-based text-to-image synthesis by improving perceptual quality of generated images. Differentiated from previous work, our synthetic image generator optimizes on perceptual loss functions that measure pixel, feature activation, and texture differences against a natural imag…
We consider image transformation problems, where an input image is transformed into an output image. Recent methods for such problems typically train feed-forward convolutional neural networks using a \emph{per-pixel} loss between the output and ground-truth images. Parallel work has shown that high-quality images can be generated by defining and optimizing \emph{perceptual} loss functions based on high-level features extracted from pretrained networks. We combine the benefits of both approaches, and propose the use of perceptual loss functions for training feed-forward networks for image tran…
City University of Hong Kong（香港城市大学）；City University of Hong Kong Shenzhen Research Institute（香港城市大学深圳研究院）；The University of Tokyo（东京大学）
Existing psychophysical studies have revealed that the cross-modal visual-tactile perception is common for humans performing daily activities. However, it is still challenging to build the algorithmic mapping from one modality space to another, namely the cross-modal visual-tactile data translation/generation, which could be potentially important for robotic operation. In this paper, we propose a deep-learning-based approach for cross-modal visual-tactile data generation by leveraging the framework of the generative adversarial networks (GANs). Our approach takes the visual image of a material…
Samsung AI Center Moscow（三星人工智能中心莫斯科）；Skolkovo Institute of Science and Technology（斯科尔科沃科学技术学院）
Many applications of deep learning for image generation use perceptual losses for either training or fine-tuning of the generator networks. The use of perceptual loss however incurs repeated forward-backward passes in a large image classification network as well as a considerable memory overhead required to store the activations of this network. It is therefore desirable or sometimes even critical to get rid of these overheads. In this work, we propose a way to train generator networks using approximations of perceptual loss that are computed without forward-backward passes. Instead, we use a …
Indian Institute of Information Technology, Sri City（印度信息技术学院斯里城校区）
In many real world scenarios, it is difficult to capture the images in the visible light spectrum (VIS) due to bad lighting conditions. However, the images can be captured in such scenarios using Near-Infrared (NIR) and Thermal (THM) cameras. The NIR and THM images contain the limited details. Thus, there is a need to transform the images from THM/NIR to VIS for better understanding. However, it is non-trivial task due to the large domain discrepancies and lack of abundant datasets. Nowadays, Generative Adversarial Network (GAN) is able to transform the images from one domain to another domain…
While it is nearly effortless for humans to quickly assess the perceptual similarity between two images, the underlying processes are thought to be quite complex. Despite this, the most widely used perceptual metrics today, such as PSNR and SSIM, are simple, shallow functions, and fail to account for many nuances of human perception. Recently, the deep learning community has found that features of the VGG network trained on ImageNet classification has been remarkably useful as a training loss for image synthesis. But how perceptual are these so-called "perceptual losses"? What elements are cri…
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；University of Chinese Academy of Sciences（中国科学院大学）
Generative Adversarial Networks (GAN) have demonstrated the potential to recover realistic details for single image super-resolution (SISR). To further improve the visual quality of super-resolved results, PIRM2018-SR Challenge employed perceptual metrics to assess the perceptual quality, such as PI, NIQE, and Ma. However, existing methods cannot directly optimize these indifferentiable perceptual metrics, which are shown to be highly correlated with human ratings. To address the problem, we propose Super-Resolution Generative Adversarial Networks with Ranker (RankSRGAN) to optimize generator …
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Shanghai AI Lab（上海人工智能实验室）
Generative Adversarial Networks (GAN) have demonstrated the potential to recover realistic details for single image super-resolution (SISR). To further improve the visual quality of super-resolved results, PIRM2018-SR Challenge employed perceptual metrics to assess the perceptual quality, such as PI, NIQE, and Ma. However, existing methods cannot directly optimize these indifferentiable perceptual metrics, which are shown to be highly correlated with human ratings. To address the problem, we propose Super-Resolution Generative Adversarial Networks with Ranker (RankSRGAN) to optimize generator …
Nanjing University of Science and Technology（南京理工大学）
Transforming a thermal infrared image into a realistic RGB image is a challenging task. In this paper we propose a deep learning method to bridge this gap. We propose learning the transformation mapping using a coarse-to-fine generator that preserves the details. Since the standard mean squared loss cannot penalize the distance between colorized and ground truth images well, we propose a composite loss function that combines content, adversarial, perceptual and total variation losses. The content loss is used to recover global image information while the latter three losses are used to synthes…
We present an approach to separating reflection from a single image. The approach uses a fully convolutional network trained end-to-end with losses that exploit low-level and high-level image information. Our loss function includes two perceptual losses: a feature loss from a visual perception network, and an adversarial loss that encodes characteristics of images in the transmission layers. We also propose a novel exclusion loss that enforces pixel-level layer separation. We create a dataset of real-world images with reflection and corresponding ground-truth transmission layers for quantitati…
Image completion has achieved significant progress due to advances in generative adversarial networks (GANs). Albeit natural-looking, the synthesized contents still lack details, especially for scenes with complex structures or images with large holes. This is because there exists a gap between low-level reconstruction loss and high-level adversarial loss. To address this issue, we introduce a perceptual network to provide mid-level guidance, which measures the semantical similarity between the synthesized and original contents in a similarity-enhanced space. We conduct a detailed analysis on …
Image colorization aims to add color information to a grayscale image in a realistic way. Recent methods mostly rely on deep learning strategies. While learning to automatically colorize an image, one can define well-suited objective functions related to the desired color output. Some of them are based on a specific type of error between the predicted image and ground truth one, while other losses rely on the comparison of perceptual properties. But, is the choice of the objective function that crucial, i.e., does it play an important role in the results? In this chapter, we aim to answer this…
Gaze redirection is the task of changing the gaze to a desired direction for a given monocular eye patch image. Many applications such as videoconferencing, films, games, and generation of training data for gaze estimation require redirecting the gaze, without distorting the appearance of the area surrounding the eye and while producing photo-realistic images. Existing methods lack the ability to generate perceptually plausible images. In this work, we present a novel method to alleviate this problem by leveraging generative adversarial training to synthesize an eye image conditioned on a targ…
Single image super resolution (SISR) is to reconstruct a high resolution image from a single low resolution image. The SISR task has been a very attractive research topic over the last two decades. In recent years, convolutional neural network (CNN) based models have achieved great performance on SISR task. Despite the breakthroughs achieved by using CNN models, there are still some problems remaining unsolved, such as how to recover high frequency details of high resolution images. Previous CNN based models always use a pixel wise loss, such as l2 loss. Although the high resolution images con…
Detecting small objects is notoriously challenging due to their low resolution and noisy representation. Existing object detection pipelines usually detect small objects through learning representations of all the objects at multiple scales. However, the performance gain of such ad hoc architectures is usually limited to pay off the computational cost. In this work, we address the small object detection problem by developing a single architecture that internally lifts representations of small objects to "super-resolved" ones, achieving similar characteristics as large objects and thus more dis…
Generative adversarial network (GAN) for image super-resolution (SR) has attracted enormous interests in recent years. However, the GAN-based SR methods only use image discriminator to distinguish SR images and high-resolution (HR) images. Image discriminator fails to discriminate images accurately since image features cannot be fully expressed. In this paper, we design a new GAN-based SR framework GAN-IMC which includes generator, image discriminator, morphological component discriminator and color discriminator. The combination of multiple feature discriminators improves the accuracy of imag…
Skolkovo Institute of Science and Technology（斯科尔科沃科技学院）
Systems that perform image manipulation using deep convolutional networks have achieved remarkable realism. Perceptual losses and losses based on adversarial discriminators are the two main classes of learning objectives behind these advances. In this work, we show how these two ideas can be combined in a principled and non-additive manner for unaligned image translation tasks. This is accomplished through a special architecture of the discriminator network inside generative adversarial learning framework. The new architecture, that we call a perceptual discriminator, embeds the convolutional …
Northwestern University（西北大学）；Universidad de Granada（格拉纳达大学）
Video super-resolution (VSR) has become one of the most critical problems in video processing. In the deep learning literature, recent works have shown the benefits of using adversarial-based and perceptual losses to improve the performance on various image restoration tasks; however, these have yet to be applied for video super-resolution. In this work, we propose a Generative Adversarial Network(GAN)-based formulation for VSR. We introduce a new generator network optimized for the VSR problem, named VSRResNet, along with a new discriminator architecture to properly guide VSRResNet during the…
Generative adversarial networks (GANs) are widely used in image generation tasks, yet the generated images are usually lack of texture details. In this paper, we propose a general framework, called Progressively Unfreezing Perceptual GAN (PUPGAN), which can generate images with fine texture details. Particularly, we propose an adaptive perceptual discriminator with a pre-trained perceptual feature extractor, which can efficiently measure the discrepancy between multi-level features of the generated and real images. In addition, we propose a progressively unfreezing scheme for the adaptive perc…
Beihang University（北京航空航天大学）；Institute for Infocomm Research（资讯通信研究院）
The generative adversarial network (GAN) is successfully applied to study the perceptual single image superresolution (SISR). However, the GAN often tends to generate images with high frequency details being inconsistent with the real ones. Inspired by conventional detail enhancement algorithms, we propose a novel prior knowledge, the detail prior, to assist the GAN in alleviating this problem and restoring more realistic details. The proposed method, named DSRGAN, includes a well designed detail extraction algorithm to capture the most important high frequency information from images. Then, t…
Image reconstruction including image restoration and denoising is a challenging problem in the field of image computing. We present a new method, called X-GANs, for reconstruction of arbitrary corrupted resource based on a variant of conditional generative adversarial networks (conditional GANs). In our method, a novel generator and multi-scale discriminators are proposed, as well as the combined adversarial losses, which integrate a VGG perceptual loss, an adversarial perceptual loss, and an elaborate corresponding point loss together based on the analysis of image feature. Our conditional GA…
Beijing University of Posts and Telecommunications（北京邮电大学）；Queen Mary University of London（伦敦玛丽女王大学）；The University of Edinburgh（爱丁堡大学）
In this work we aim to develop a universal sketch grouper. That is, a grouper that can be applied to sketches of any category in any domain to group constituent strokes/segments into semantically meaningful object parts. The first obstacle to this goal is the lack of large-scale datasets with grouping annotation. To overcome this, we contribute the largest sketch perceptual grouping (SPG) dataset to date, consisting of 20,000 unique sketches evenly distributed over 25 object categories. Furthermore, we propose a novel deep universal perceptual grouping model. The model is learned with both gen…
Many super-resolution (SR) models are optimized for high performance only and therefore lack efficiency due to large model complexity. As large models are often not practical in real-world applications, we investigate and propose novel loss functions, to enable SR with high perceptual quality from much more efficient models. The representative power for a given low-complexity generator network can only be fully leveraged by strong guidance towards the optimal set of parameters. We show that it is possible to improve the performance of a recently introduced efficient generator architecture sole…
NNAISENSE；Universita della Svizzera italiana（瑞士意大利语区大学）
This paper introduces a neural style transfer model to generate a stylized image conditioning on a set of examples describing the desired style. The proposed solution produces high-quality images even in the zero-shot setting and allows for more freedom in changes to the content geometry. This is made possible by introducing a novel Two-Stage Peer-Regularization Layer that recombines style and content in latent space by means of a custom graph convolutional layer. Contrary to the vast majority of existing solutions, our model does not depend on any pre-trained networks for computing perceptual…
University of Toronto（多伦多大学）；University of Colorado, Boulder（科罗拉多大学博尔德分校）
Deep networks are increasingly being applied to problems involving image synthesis, e.g., generating images from textual descriptions and reconstructing an input image from a compact representation. Supervised training of image-synthesis networks typically uses a pixel-wise loss (PL) to indicate the mismatch between a generated image and its corresponding target image. We propose instead to use a loss function that is better calibrated to human perceptual judgments of image quality: the multiscale structural-similarity score (MS-SSIM). Because MS-SSIM is differentiable, it is easily incorporat…
Text image super-resolution is a unique and important task to enhance readability of text images to humans. It is widely used as pre-processing in scene text recognition. However, due to the complex degradation in natural scenes, recovering high-resolution texts from the low-resolution inputs is ambiguous and challenging. Existing methods mainly leverage deep neural networks trained with pixel-wise losses designed for natural image reconstruction, which ignore the unique character characteristics of texts. A few works proposed content-based losses. However, they only focus on text recognizers'…
Learning a typical image enhancement pipeline involves minimization of a loss function between enhanced and reference images. While L1 and L2 losses are perhaps the most widely used functions for this purpose, they do not necessarily lead to perceptually compelling results. In this paper, we show that adding a learned no-reference image quality metric to the loss can significantly improve enhancement operators. This metric is implemented using a CNN (convolutional neural network) trained on a large-scale dataset labelled with aesthetic preferences of human raters. This loss allows us to conven…
Autoencoders are commonly trained using element-wise loss. However, element-wise loss disregards high-level structures in the image which can lead to embeddings that disregard them as well. A recent improvement to autoencoders that helps alleviate this problem is the use of perceptual loss. This work investigates perceptual loss from the perspective of encoder embeddings themselves. Autoencoders are trained to embed images from three different computer vision datasets using perceptual loss based on a pretrained model as well as pixel-wise loss. A host of different predictors are trained to per…
Features obtained from object recognition CNNs have been widely used for measuring perceptual similarities between images. Such differentiable metrics can be used as perceptual learning losses to train image enhancement models. However, the choice of the distance function between input and target features may have a consequential impact on the performance of the trained model. While using the norm of the difference between extracted features leads to limited hallucination of details, measuring the distance between distributions of features may generate more textures; yet also more unrealistic …
SROBB: Targeted Perceptual Loss for Single Image Super-Resolution（SROBB：面向单幅图像超分辨率的感知损失）
By benefiting from perceptual losses, recent studies have improved significantly the performance of the super-resolution task, where a high-resolution image is resolved from its low-resolution counterpart. Although such objective functions generate near-photorealistic results, their capability is limited, since they estimate the reconstruction error for an entire image in the same way, without considering any semantic information. In this paper, we propose a novel method to benefit from perceptual loss in a more objective way. We optimize a deep network-based decoder with a targeted objective …
The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；East China Normal University（华东师范大学）
Pursuing realistic results according to human visual perception is the central concern in the image transformation tasks. Perceptual learning approaches like perceptual loss are empirically powerful for such tasks but they usually rely on the pre-trained classification network to provide features, which are not necessarily optimal in terms of visual perception of image transformation. In this paper, we argue that, among the features representation from the pre-trained classification network, only limited dimensions are related to human visual perception, while others are irrelevant, although b…
Seoul National University（首尔国立大学）；Samsung Electronics（三星电子）
Single-image super-resolution (SISR) networks trained with perceptual and adversarial losses provide high-contrast outputs compared to those of networks trained with distortion-oriented losses, such as L1 or L2. However, it has been shown that using a single perceptual loss is insufficient for accurately restoring locally varying diverse shapes in images, often generating undesirable artifacts or unnatural details. For this reason, combinations of various losses, such as perceptual, adversarial, and distortion losses, have been attempted, yet it remains challenging to find optimal combinations…
Technion–Israel Institute of Technology（以色列理工学院）；ETH Zurich（苏黎世联邦理工学院）
This paper reports on the 2018 PIRM challenge on perceptual super-resolution (SR), held in conjunction with the Perceptual Image Restoration and Manipulation (PIRM) workshop at ECCV 2018. In contrast to previous SR challenges, our evaluation methodology jointly quantifies accuracy and perceptual quality, therefore enabling perceptual-driven methods to compete alongside algorithms that target PSNR maximization. Twenty-one participating teams introduced algorithms which well-improved upon the existing state-of-the-art methods in perceptual SR, as confirmed by a human opinion study. We also analy…
Beijing University of Posts and Telecommunications（北京邮电大学）；Peng Cheng Laboratory（鹏城实验室）
As one novel approach to realize end-to-end wireless image semantic transmission, deep learning-based joint source-channel coding (deep JSCC) method is emerging in both deep learning and communication communities. However, current deep JSCC image transmission systems are typically optimized for traditional distortion metrics such as peak signal-to-noise ratio (PSNR) or multi-scale structural similarity (MS-SSIM). But for low transmission rates, due to the imperfect wireless channel, these distortion metrics lose significance as they favor pixel-wise preservation. To account for human visual pe…
Indian Institute of Technology, Madras（印度理工学院马德拉斯分校）
Convolutional neural network (CNN) based methods have recently achieved great success for image super-resolution (SR). However, most deep CNN based SR models attempt to improve distortion measures (e.g. PSNR, SSIM, IFC, VIF) while resulting in poor quantified perceptual quality (e.g. human opinion score, no-reference quality measures such as NIQE). Few works have attempted to improve the perceptual quality at the cost of performance reduction in distortion measures. A very recent study has revealed that distortion and perceptual quality are at odds with each other and there is always a trade-o…
Luleå University of Technology（吕勒奥理工大学）；EISLAB（电子信息科学实验室）
This work investigates three methods for calculating loss for autoencoder-based pretraining of image encoders: The commonly used reconstruction loss, the more recently introduced deep perceptual similarity loss, and a feature prediction loss proposed here; the latter turning out to be the most efficient choice. Standard auto-encoder pretraining for deep learning tasks is done by comparing the input image and the reconstructed image. Recent work shows that predictions based on embeddings generated by image autoencoders can be improved by training with perceptual loss, i.e., by adding a loss net…
Despite a rapid rise in the quality of built-in smartphone cameras, their physical limitations - small sensor size, compact lenses and the lack of specific hardware, - impede them to achieve the quality results of DSLR cameras. In this work we present an end-to-end deep learning approach that bridges this gap by translating ordinary photos into DSLR-quality images. We propose learning the translation function using a residual convolutional neural network that improves both color rendition and image sharpness. Since the standard mean squared loss is not well suited for measuring perceptual imag…
Recently, it has been shown that in super-resolution, there exists a tradeoff relationship between the quantitative and perceptual quality of super-resolved images, which correspond to the similarity to the ground-truth images and the naturalness, respectively. In this paper, we propose a novel super-resolution method that can improve the perceptual quality of the upscaled images while preserving the conventional quantitative performance. The proposed method employs a deep network for multi-pass upscaling in company with a discriminator network and two quantitative score predictor networks. Ex…
The University of Tokyo（东京大学）；Data61-CSIRO（澳大利亚联邦科学与工业研究组织数据61研究所）；Australian National University（澳大利亚国立大学）
This paper tackles high-dynamic-range (HDR) image reconstruction given only a single low-dynamic-range (LDR) image as input. While the existing methods focus on minimizing the mean-squared-error (MSE) between the target and reconstructed images, we minimize a hybrid loss that consists of perceptual and adversarial losses in addition to HDR-reconstruction loss. The reconstruction loss instead of MSE is more suitable for HDR since it puts more weight on both over- and under- exposed areas. It makes the reconstruction faithful to the input. Perceptual loss enables the networks to utilize knowledg…
Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；Amazon Research（亚马逊研究院）
While implicit generative models such as GANs have shown impressive results in high quality image reconstruction and manipulation using a combination of various losses, we consider a simpler approach leading to surprisingly strong results. We show that texture loss alone allows the generation of perceptually high quality images. We provide a better understanding of texture constraining mechanism and develop a novel semantically guided texture constraining method for further improvement. Using a recently developed perceptual metric employing "deep features" and termed LPIPS, the method obtains …
Signal Processing Lab (LTS5) EPFL（信号处理实验室（LTS5）洛桑联邦理工学院）
Existing reference (RF)-based super-resolution (SR) models try to improve perceptual quality in SR under the assumption of the availability of high-resolution RF images paired with low-resolution (LR) inputs at testing. As the RF images should be similar in terms of content, colors, contrast, etc. to the test image, this hinders the applicability in a real scenario. Other approaches to increase the perceptual quality of images, including perceptual loss and adversarial losses, tend to dramatically decrease fidelity to the ground-truth through significant decreases in PSNR/SSIM. Addressing both…
Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）
Deep Convolutional Neural Network (CNN) features have been demonstrated to be effective perceptual quality features. The perceptual loss, based on feature maps of pre-trained CNN's has proven to be remarkably effective for CNN based perceptual image restoration problems. In this work, taking inspiration from the the Human Visual System (HVS) and visual perception, we propose a spatial attention mechanism based on the dependency human contrast sensitivity on spatial frequency. We identify regions in input images, based on the underlying spatial frequency, which are not generally well reconstruc…
