In recent years, Generative Adversarial Networks (GANs) have improved steadily towards generating increasingly impressive real-world images. It is useful to steer the image generation process for purposes such as content creation. This can be done by conditioning the model on additional information. However, when conditioning on additional information, there still exists a large set of images that agree with a particular conditioning. This makes it unlikely that the generated image is exactly as envisioned by a user, which is problematic for practical content creation scenarios such as generating facial composites or stock photos. To solve this problem, we propose a single pipeline for text-to-image generation and manipulation. In the first part of our pipeline we introduce textStyleGAN, a model that is conditioned on text. In the second part of our pipeline we make use of the pre-trained weights of textStyleGAN to perform semantic facial image manipulation. The approach works by finding semantic directions in latent space. We show that this method can be used to manipulate facial images for a wide range of attributes. Finally, we introduce the CelebTD-HQ dataset, an extension to CelebA-HQ, consisting of faces and corresponding textual descriptions.
We present a new method for synthesizing high-resolution photo-realistic images from semantic label maps using conditional generative adversarial networks (conditional GANs). Conditional GANs have enabled a variety of applications, but the results are often limited to low-resolution and still far from realistic. In this work, we generate 2048x1024 visually appealing results with a novel adversarial loss, as well as new multi-scale generator and discriminator architectures. Furthermore, we extend our framework to interactive visual manipulation with two additional features. First, we incorporat…
Institute of Computing Technology, CAS（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Peng Cheng Laboratory（鹏城实验室）
Conditional image generation is an active research topic including text2image and image translation. Recently image manipulation with linguistic instruction brings new challenges of multimodal conditional generation. However, traditional conditional image generation models mainly focus on generating high-quality and visually realistic images, and lack resolving the partial consistency between image and instruction. To address this issue, we propose an Increment Reasoning Generative Adversarial Network (IR-GAN), which aims to reason the consistency between visual increment in images and semanti…
Altering the content of an image with photo editing tools is a tedious task for an inexperienced user. Especially, when modifying the visual attributes of a specific object in an image without affecting other constituents such as background etc. To simplify the process of image manipulation and to provide more control to users, it is better to utilize a simpler interface like natural language. Therefore, in this paper, we address the challenge of manipulating images using natural language description. We propose the Two-sidEd Attentive conditional Generative Adversarial Network (TEA-cGAN) to g…
University of Science and Technology of China（中国科学技术大学）；Microsoft Research（微软研究院）
Portrait editing is a popular subject in photo manipulation. The Generative Adversarial Network (GAN) advances the generating of realistic faces and allows more face editing. In this paper, we argue about three issues in existing techniques: diversity, quality, and controllability for portrait synthesis and editing. To address these issues, we propose a novel end-to-end learning framework that leverages conditional GANs guided by provided face masks for generating faces. The framework learns feature embeddings for every face component (e.g., mouth, hair, eye), separately, contributing to bette…
International Institute of Information Technology, Bangalore（国际信息技术学院班加罗尔分校）；Indian Institute of Technology, Madras（印度理工学院马德拉斯分校）
Learning a disentangled representation of the latent space has become one of the most fundamental problems studied in computer vision. Recently, many Generative Adversarial Networks (GANs) have shown promising results in generating high fidelity images. However, studies to understand the semantic layout of the latent space of pre-trained models are still limited. Several works train conditional GANs to generate faces with required semantic attributes. Unfortunately, in these attempts, the generated output is often not as photo-realistic as the unconditional state-of-the-art models. Besides, th…
Conditional generative models of high-dimensional images have many applications, but supervision signals from conditions to images can be expensive to acquire. This paper describes Diffusion-Decoding models with Contrastive representations (D2C), a paradigm for training unconditional variational autoencoders (VAEs) for few-shot conditional image generation. D2C uses a learned diffusion-based prior over the latent representations to improve generation and contrastive self-supervised learning to improve representation quality. D2C can adapt to novel generation tasks conditioned on labels or mani…
The goal of attribute manipulation is to control specified attribute(s) in given images. Prior work approaches this problem by learning disentangled representations for each attribute that enables it to manipulate the encoded source attributes to the target attributes. However, encoded attributes are often correlated with relevant image content. Thus, the source attribute information can often be hidden in the disentangled features, leading to unwanted image editing effects. In this paper, we propose an Attribute Information Removal and Reconstruction (AIRR) network that prevents such informat…
Fine-grained facial expression manipulation is a challenging problem, as fine-grained expression details are difficult to be captured. Most existing expression manipulation methods resort to discrete expression labels, which mainly edit global expressions and ignore the manipulation of fine details. To tackle this limitation, we propose an end-to-end expression-guided generative adversarial network (EGGAN), which utilizes structured latent codes and continuous expression labels as input to generate images with expected expressions. Specifically, we adopt an adversarial autoencoder to map a sou…
Controllable retinal image synthesis using conditional StyleGAN and latent space manipulation for improved diagnosis and grading of diabetic retinopathy
Amirkabir University of Technology（阿米尔卡比尔理工大学）；Tehran Medical Sciences, Islamic Azad University（伊斯兰阿扎德大学德黑兰医学科学分校）
Generative Adversarial Networks (GANs) have recently achieved significant improvement on paired/unpaired image-to-image translation, such as photo$\rightarrow$ sketch and artist painting style transfer. However, existing models can only be capable of transferring the low-level information (e.g. color or texture changes), but fail to edit high-level semantic meanings (e.g., geometric structure or content) of objects. On the other hand, while some researches can synthesize compelling real-world images given a class label or caption, they cannot condition on arbitrary shapes or structures, which …
Exploring Compositional Visual Generation with Latent Classifier Guidance
University of California, San Diego（加州大学圣地亚哥分校）；The Pennsylvania State University（宾夕法尼亚州立大学）；NEC Laboratories America（NEC美国实验室）；Northwestern University（西北大学）
Skolkovo Institute of Science and Technology（斯科尔科沃科学技术学院）
In this work, we consider the task of generating highly-realistic images of a given face with a redirected gaze. We treat this problem as a specific instance of conditional image generation and suggest a new deep architecture that can handle this task very well as revealed by numerical comparison with prior art and a user study. Our deep architecture performs coarse-to-fine warping with an additional intensity correction of individual pixels. All these operations are performed in a feed-forward manner, and the parameters associated with different operations are learned jointly in the end-to-en…
Google Research（谷歌研究院）；University of California, Merced（加利福尼亚大学默塞德分校）；Carnegie Mellon University（卡内基梅隆大学）；Waymo；University of Michigan（密歇根大学）；Georgia Institute of Technology（佐治亚理工学院）
In recent years, text-guided image manipulation has gained increasing attention in the multimedia and computer vision community. The input to conditional image generation has evolved from image-only to multimodality. In this paper, we study a setting that allows users to edit an image with multiple objects using complex text instructions to add, remove, or change the objects. The inputs of the task are multimodal including (1) a reference image and (2) an instruction in natural language that describes desired modifications to the image. We propose a GAN-based method to tackle this problem. The…
Purdue University（普渡大学）；Politecnico di Milano（米兰理工大学）
The widespread availability of image editing tools and improvements in image processing techniques allow image manipulation to be very easy. Oftentimes, easy-to-use yet sophisticated image manipulation tools yields distortions/changes imperceptible to the human observer. Distribution of forged images can have drastic ramifications, especially when coupled with the speed and vastness of the Internet. Therefore, verifying image integrity poses an immense and important challenge to the digital forensic community. Satellite images specifically can be modified in a number of ways, including the ins…
A conditional Generative Adversarial Network allows for generating samples conditioned on certain external information. Being able to recover latent and conditional vectors from a condi- tional GAN can be potentially valuable in various applications, ranging from image manipulation for entertaining purposes to diagnosis of the neural networks for security purposes. In this work, we show that it is possible to recover both latent and conditional vectors from generated images given the generator of a conditional generative adversarial network. Such a recovery is not trivial due to the often mult…
We examined the use of modern Generative Adversarial Nets to generate novel images of oil paintings using the Painter By Numbers dataset. We implemented Spectral Normalization GAN (SN-GAN) and Spectral Normalization GAN with Gradient Penalty, and compared their outputs to a Deep Convolutional GAN. Visually, and quantitatively according to the Sliced Wasserstein Distance metric, we determined that the SN-GAN produced paintings that were most comparable to our training dataset. We then performed a series of experiments to add supervised conditioning to SN-GAN, the culmination of which is what we…
While facial attribute manipulation of 2D images via Generative Adversarial Networks (GANs) has become common in computer vision and graphics due to its many practical uses, research on 3D attribute manipulation is relatively undeveloped. Existing 3D attribute manipulation methods are limited because the same semantic changes are applied to every 3D face. The key challenge for developing better 3D attribute control methods is the lack of paired training data in which one attribute is changed while other attributes are held fixed -- e.g., a pair of 3D faces where one is male and the other is fe…
Hong Kong University of Science and Technology（香港科技大学）；Carnegie Mellon University（卡内基梅隆大学）；Petuum Inc.（Petuum公司）
Many problems in image processing and computer vision (e.g. colorization, style transfer) can be posed as 'manipulating' an input image into a corresponding output image given a user-specified guiding signal. A holy-grail solution towards generic image manipulation should be able to efficiently alter an input image with any personalized signals (even signals unseen during training), such as diverse paintings and arbitrary descriptive attributes. However, existing methods are either inefficient to simultaneously process multiple signals (let alone generalize to unseen signals), or unable to han…
Stanford University（斯坦福大学）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）；NVIDIA（英伟达）；Caltech（加州理工学院）
Manipulating volumetric deformable objects in the real world, like plush toys and pizza dough, bring substantial challenges due to infinite shape variations, non-rigid motions, and partial observability. We introduce ACID, an action-conditional visual dynamics model for volumetric deformable objects based on structured implicit neural representations. ACID integrates two new techniques: implicit representations for action-conditional dynamics and geodesics-based contrastive learning. To represent deformable dynamics from partial RGB-D observations, we learn implicit representations of occupanc…
University of Southern California（南加利福尼亚大学）；Emory University（埃默里大学）
Previous methods have dealt with discrete manipulation of facial attributes such as smile, sad, angry, surprise etc, out of canonical expressions and they are not scalable, operating in single modality. In this paper, we propose a novel framework that supports continuous edits and multi-modality portrait manipulation using adversarial learning. Specifically, we adapt cycle-consistency into the conditional setting by leveraging additional facial landmarks information. This has two effects: first cycle mapping induces bidirectional manipulation and identity preserving; second pairing samples fro…
In this paper, we present DeepSIM, a generative model for conditional image manipulation based on a single image. We find that extensive augmentation is key for enabling single image training, and incorporate the use of thin-plate-spline (TPS) as an effective augmentation. Our network learns to map between a primitive representation of the image to the image itself. The choice of a primitive representation has an impact on the ease and expressiveness of the manipulations and can be automatic (e.g. edges), manual (e.g. segmentation) or hybrid such as edges on top of segmentations. At manipulati…
Facial expression manipulation aims at editing facial expression with a given condition. Previous methods edit an input image under the guidance of a discrete emotion label or absolute condition (e.g., facial action units) to possess the desired expression. However, these methods either suffer from changing condition-irrelevant regions or are inefficient for fine-grained editing. In this study, we take these two objectives into consideration and propose a novel method. First, we replace continuous absolute condition with relative condition, specifically, relative action units. With relative ac…
Face modification systems using deep learning have become increasingly powerful and accessible. Given images of a person's face, such systems can generate new images of that same person under different expressions and poses. Some systems can also modify targeted attributes such as hair color or age. This type of manipulated images and video have been coined Deepfakes. In order to prevent a malicious user from generating modified images of a person without their consent we tackle the new problem of generating adversarial attacks against such image translation systems, which disrupt the resultin…
In this paper, we present DeepSIM, a generative model for conditional image manipulation based on a single image. We find that extensive augmentation is key for enabling single image training, and incorporate the use of thin-plate-spline (TPS) as an effective augmentation. Our network learns to map between a primitive representation of the image to the image itself. The choice of a primitive representation has an impact on the ease and expressiveness of the manipulations and can be automatic (e.g. edges), manual (e.g. segmentation) or hybrid such as edges on top of segmentations. At manipulati…
Harvard Medical School（哈佛医学院）；National University of Singapore（新加坡国立大学）；Harvard University（哈佛大学）；Boston Children’s Hospital（波士顿儿童医院）；Center for Brains, Minds and Machines（大脑、心智与机器中心）
Artificial neural networks (ANNs) are considered the current best models of biological vision. ANNs are the best predictors of neural activity in the ventral stream; moreover, recent work has demonstrated that ANN models fitted to neuronal activity can guide the synthesis of images that drive pre-specified response patterns in small neuronal populations. Despite the success in predicting and steering firing activity, these results have not been connected with perceptual or behavioral changes. Here we propose an array of methods for creating minimal, targeted image perturbations that lead to ch…
The manipulation of latent space has recently become an interesting topic in the field of generative models. Recent research shows that latent directions can be used to manipulate images towards certain attributes. However, controlling the generation process of 3D generative models remains a challenge. In this work, we propose a novel 3D manipulation method that can manipulate both the shape and texture of the model using text or image-based prompts such as 'a young face' or 'a surprised face'. We leverage the power of Contrastive Language-Image Pre-training (CLIP) model and a pre-trained 3D G…
KAIST Graduate School of AI, Korea Advanced Institute of Science and Technology（韩国科学技术院人工智能研究生院）
While recent NeRF-based generative models achieve the generation of diverse 3D-aware images, these approaches have limitations when generating images that contain user-specified characteristics. In this paper, we propose a novel model, referred to as the conditional generative neural radiance fields (CG-NeRF), which can generate multi-view images reflecting extra input conditions such as images or texts. While preserving the common characteristics of a given input condition, the proposed model generates diverse images in fine detail. We propose: 1) a novel unified architecture which disentangl…
Shenzhen Research Institute, The Hong Kong Polytechnic University（香港理工大学深圳研究院）；The Hong Kong Polytechnic University（香港理工大学）；University of Oxford（牛津大学）
In this paper, we study the problem of 3D scene geometry decomposition and manipulation from 2D views. By leveraging the recent implicit neural representation techniques, particularly the appealing neural radiance fields, we introduce an object field component to learn unique codes for all individual objects in 3D space only from 2D supervision. The key to this component is a series of carefully designed loss functions to enable every 3D point, especially in non-occupied space, to be effectively optimized even without 3D labels. In addition, we introduce an inverse query algorithm to freely ma…
