SSD-GAN: Measuring the Realness in the Spatial and Spectral Domains
School of Electronic and Computer Engineering, Peking University（北京大学电子与计算机工程学院）；Peng Cheng Laboratory（鹏城实验室）；Advanced Institute of Information Technology, Peking University（北京大学信息科学技术学院高级研究院）；Tencent America（腾讯美国公司）
This paper observes that there is an issue of high frequencies missing in the discriminator of standard GAN, and we reveal it stems from downsampling layers employed in the network architecture. This issue makes the generator lack the incentive from the discriminator to learn high-frequency content of data, resulting in a significant spectrum discrepancy between generated images and real images. Since the Fourier transform is a bijective mapping, we argue that reducing this spectrum discrepancy would boost the performance of GANs. To this end, we introduce SSD-GAN, an enhancement of GANs to alleviate the spectral information loss in the discriminator. Specifically, we propose to embed a frequency-aware classifier into the discriminator to measure the realness of the input in both the spatial and spectral domains. With the enhanced discriminator, the generator of SSD-GAN is encouraged to learn high-frequency content of real data and generate exact details. The proposed method is general and can be easily integrated into most existing GANs framework without excessive cost. The effectiveness of SSD-GAN is validated on various network architectures, objective functions, and datasets. Code will be available at https://github.com/cyq373/SSD-GAN.
The Chinese University of Hong Kong（香港中文大学）；Nanyang Technological University（南洋理工大学）
While generative adversarial networks (GAN) have been widely adopted in various topics, in this paper we generalize the standard GAN to a new perspective by treating realness as a random variable that can be estimated from multiple angles. In this generalized framework, referred to as RealnessGAN, the discriminator outputs a distribution as the measure of realness. While RealnessGAN shares similar theoretical guarantees with the standard GAN, it provides more insights on adversarial learning. Compared to multiple baselines, RealnessGAN provides stronger guidance for the generator, achieving im…
University College London（伦敦大学学院）；Odin Vision（奥丁视觉（Odin Vision））；Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS)（惠康/工程与物理科学研究委员会介入与外科科学中心（WEISS））
Endoscopic examinations are used to inspect the throat, stomach and bowel for polyps which could develop into cancer. Machine learning systems can be trained to process colonoscopy images and detect polyps. However, these systems tend to perform poorly on objects which appear visually small in the images. It is shown here that combining the single-shot detector as a region proposal network with an adversarially-trained generator to upsample small region proposals can significantly improve the detection of visually-small polyps. The Dynamic SSD-GAN pipeline introduced in this paper achieved a 1…
Xi’an Jiaotong-Liverpool University（西交利物浦大学）；University of Liverpool（利物浦大学）；Duke Kunshan University（昆山杜克大学）
Generating consistent and high-quality images from given texts is essential for visual-language understanding. Although impressive results have been achieved in generating high-quality images, text-image consistency is still a major concern in existing GAN-based methods. Particularly, the most popular metric $R$-precision may not accurately reflect the text-image consistency, often resulting in very misleading semantics in the generated images. Albeit its significance, how to design a better text-image consistency metric surprisingly remains under-explored in the community. In this paper, we m…
In this work, we examine the feasibility of applying Deep Convolutional Generative Adversarial Networks (DCGANs) with Single Shot Detector (SSD) as data-processing technique to handle with the challenge of pedestrian detection in the wild. Specifically, we attempted to use in-fill completion (where a portion of the image is masked) to generate random transformations of images with portions missing to expand existing labelled datasets. In our work, GAN has been trained intensively on low resolution images, in order to neutralize the challenges of the pedestrian detection in the wild, and consid…
Peking University Shenzhen Graduate School（北京大学深圳研究生院）；Peng Cheng Laboratory（鹏城实验室）
Emerging high-quality face restoration (FR) methods often utilize pre-trained GAN models (\textit{i.e.}, StyleGAN2) as GAN Prior. However, these methods usually struggle to balance realness and fidelity when facing various degradation levels. Besides, there is still a noticeable visual quality gap compared with pre-trained GAN models. In this paper, we propose a novel GAN Prior based degradation-aware feature interpolation network, dubbed Panini-Net, for FR tasks by explicitly learning the abstract representations to distinguish various degradations. Specifically, an unsupervised degradation r…
Nanyang Technological University（南洋理工大学）；SenseTime Research（商汤科技研究院）；Shanghai AI Laboratory（上海人工智能实验室）
Recovering a textured 3D mesh from a monocular image is highly challenging, particularly for in-the-wild objects that lack 3D ground truths. In this work, we present MeshInversion, a novel framework to improve the reconstruction by exploiting the generative prior of a 3D GAN pre-trained for 3D textured mesh synthesis. Reconstruction is achieved by searching for a latent space in the 3D GAN that best resembles the target mesh in accordance with the single view observation. Since the pre-trained GAN encapsulates rich 3D semantics in terms of mesh geometry and texture, searching within the GAN ma…
Applied Research Center (ARC), Tencent PCG（腾讯平台与内容事业群应用研究中心）
Blind face restoration usually relies on facial priors, such as facial geometry prior or reference prior, to restore realistic and faithful details. However, very low-quality inputs cannot offer accurate geometric prior while high-quality references are inaccessible, limiting the applicability in real-world scenarios. In this work, we propose GFP-GAN that leverages rich and diverse priors encapsulated in a pretrained face GAN for blind face restoration. This Generative Facial Prior (GFP) is incorporated into the face restoration process via novel channel-split spatial feature transform layers,…
This research study proposes using Generative Adversarial Networks (GAN) that incorporate a two-dimensional measure of human memorability to generate memorable or non-memorable images of scenes. The memorability of the generated images is evaluated by modelling Visual Memory Schemas (VMS), which correspond to mental representations that human observers use to encode an image into memory. The VMS model is based upon the results of memory experiments conducted on human observers, and provides a 2D map of memorability. We impose a memorability constraint upon the latent space of a GAN by employin…
JD AI（京东人工智能研究院）；Central Academy of Fine Arts（中央美术学院）
Previous works on font generation mainly focus on the standard print fonts where character's shape is stable and strokes are clearly separated. There is rare research on brush handwriting font generation, which involves holistic structure changes and complex strokes transfer. To address this issue, we propose a novel GAN-based image translation model by integrating the skeleton information. We first extract the skeleton from training images, then design an image encoder and a skeleton encoder to extract corresponding features. A self-attentive refined attention module is devised to guide the m…
College of Computer Science and Software Engineering, Shenzhen University（深圳大学计算机与软件学院）；Shenzhen Institute of Artificial Intelligence and Robotics for Society（深圳人工智能与机器人研究院）；Guangdong Key Laboratory of Intelligent Information Processing, Shenzhen University（深圳大学广东省智能信息处理重点实验室）
Generative Adversarial Networks (GANs) have been widely adopted in various fields. However, existing GANs generally are not able to preserve the manifold of data space, mainly due to the simple representation of discriminator for the real/generated data. To address such open challenges, this paper proposes Manifold-preserved GANs (MaF-GANs), which generalize Wasserstein GANs into high-dimensional form. Specifically, to improve the representation of data, the discriminator in MaF-GANs is designed to map data into a high-dimensional manifold. Furthermore, to stabilize the training of MaF-GANs, a…
The quality of industrial components is critical to the production of special equipment such as robots. Defect inspection of these components is an efficient way to ensure quality. In this paper, we propose a hybrid network, SSD-Faster Net, for industrial defect inspection of rails, insulators, commutators etc. SSD-Faster Net is a two-stage network, including SSD for quickly locating defective blocks, and an improved Faster R-CNN for defect segmentation. For the former, we propose a novel slice localization mechanism to help SSD scan quickly. The second stage is based on improved Faster R-CNN,…
University of Trento（特伦托大学）；University of Oxford（牛津大学）；Huawei Research Ireland（华为爱尔兰研究院）
We present a novel Bipartite Graph Reasoning GAN (BiGraphGAN) for the challenging person image generation task. The proposed graph generator mainly consists of two novel blocks that aim to model the pose-to-pose and pose-to-image relations, respectively. Specifically, the proposed Bipartite Graph Reasoning (BGR) block aims to reason the crossing long-range relations between the source pose and the target pose in a bipartite graph, which mitigates some challenges caused by pose deformation. Moreover, we propose a new Interaction-and-Aggregation (IA) block to effectively update and enhance the f…
Image inpainting aims at restoring missing region of corrupted images, which has many applications such as image restoration and object removal. However, current GAN-based inpainting models fail to explicitly consider the semantic consistency between restored images and original images. Forexample, given a male image with image region of one eye missing, current models may restore it with a female eye. This is due to the ambiguity of GAN-based inpainting models: these models can generate many possible restorations given a missing region. To address this limitation, our key insight is that sema…
We present a novel discriminator for GANs that improves realness and diversity of generated samples by learning a structured hypersphere embedding space using spherical circles. The proposed discriminator learns to populate realistic samples around the longest spherical circle, i.e., a great circle, while pushing unrealistic samples toward the poles perpendicular to the great circle. Since longer circles occupy larger area on the hypersphere, they encourage more diversity in representation learning, and vice versa. Discriminating samples based on their corresponding spherical circles can thus …
ETH Zurich（苏黎世联邦理工学院）；Terminus Group（特斯联集团）；University of Oxford（牛津大学）；University of Trento（特伦托大学）
We present a novel bipartite graph reasoning Generative Adversarial Network (BiGraphGAN) for two challenging tasks: person pose and facial image synthesis. The proposed graph generator consists of two novel blocks that aim to model the pose-to-pose and pose-to-image relations, respectively. Specifically, the proposed bipartite graph reasoning (BGR) block aims to reason the long-range cross relations between the source and target pose in a bipartite graph, which mitigates some of the challenges caused by pose deformation. Moreover, we propose a new interaction-and-aggregation (IA) block to effe…
Peking University Shenzhen Graduate School（北京大学深圳研究生院）；Peng Cheng Laboratory（鹏城实验室）
Consistency and realness have always been the two critical issues of image super-resolution. While the realness has been dramatically improved with the use of GAN prior, the state-of-the-art methods still suffer inconsistencies in local structures and colors (e.g., tooth and eyes). In this paper, we show that these inconsistencies can be analytically eliminated by learning only the null-space component while fixing the range-space part. Further, we design a pooling-based decomposition (PD), a universal range-null space decomposition for super-resolution tasks, which is concise, fast, and param…
Northumbria University（诺森比亚大学）；Imam Mohammed ibn Saud Islamic University（伊玛目穆罕默德·本·沙特伊斯兰大学）
Generative adversarial networks (GANs) have been promising for many computer vision problems due to their powerful capabilities to enhance the data for training and test. In this paper, we leveraged GANs and proposed a new architecture with a cascaded Single Shot Detector (SSD) for pedestrian detection at distance, which is yet a challenge due to the varied sizes of pedestrians in videos at distance. To overcome the low-resolution issues in pedestrian detection at distance, DCGAN is employed to improve the resolution first to reconstruct more discriminative features for a SSD to detect objects…
The Chinese University of Hong Kong（香港中文大学）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；University of Chinese Academy of Sciences（中国科学院大学）；Nanyang Technological University（南洋理工大学）
The Super-Resolution Generative Adversarial Network (SRGAN) is a seminal work that is capable of generating realistic textures during single image super-resolution. However, the hallucinated details are often accompanied with unpleasant artifacts. To further enhance the visual quality, we thoroughly study three key components of SRGAN - network architecture, adversarial loss and perceptual loss, and improve each of them to derive an Enhanced SRGAN (ESRGAN). In particular, we introduce the Residual-in-Residual Dense Block (RRDB) without batch normalization as the basic network building unit. Mo…
Adversarial examples are data points misclassified by neural networks. Originally, adversarial examples were limited to adding small perturbations to a given image. Recent work introduced the generalized concept of unrestricted adversarial examples, without limits on the added perturbations. In this paper, we introduce a new category of attacks that create unrestricted adversarial examples for object detection. Our key idea is to generate adversarial objects that are unrelated to the classes identified by the target object detector. Different from previous attacks, we use off-the-shelf Generat…
University of Alberta（阿尔伯塔大学）；Ludwig-Maximilians-Universität München（慕尼黑路德维希-马克西米利安大学（慕尼黑大学））；Alberta Geological Survey（阿尔伯塔地质调查局）；Alberta Energy Regulator（阿尔伯塔能源监管局）
The detection performance of small objects in remote sensing images is not satisfactory compared to large objects, especially in low-resolution and noisy images. A generative adversarial network (GAN)-based model called enhanced super-resolution GAN (ESRGAN) shows remarkable image enhancement performance, but reconstructed images miss high-frequency edge information. Therefore, object detection performance degrades for small objects on recovered noisy and low-resolution remote sensing images. Inspired by the success of edge enhanced GAN (EEGAN) and ESRGAN, we apply a new edge-enhanced super-re…
