Taesung Park, Jun-Yan Zhu, Oliver Wang, Jingwan Lu, Eli Shechtman, Alexei A. Efros, Richard Zhang
备注：
NeurIPS 2020. Please visit https://taesung.me/SwappingAutoencoder/ for an introductory video. v2 mainly contains reorganization of the Introduction and Broader Impact section
Deep generative models have become increasingly effective at producing realistic images from randomly sampled seeds, but using such models for controllable manipulation of existing images remains challenging. We propose the Swapping Autoencoder, a deep model designed specifically for image manipulation, rather than random sampling. The key idea is to encode an image with two independent components and enforce that any swapped combination maps to a realistic image. In particular, we encourage the components to represent structure and texture, by enforcing one component to encode co-occurrent patch statistics across different parts of an image. As our method is trained with an encoder, finding the latent codes for a new input image becomes trivial, rather than cumbersome. As a result, it can be used to manipulate real input images in various ways, including texture swapping, local and global editing, and latent code vector arithmetic. Experiments on multiple datasets show that our model produces better results and is substantially more efficient compared to recent generative models.
We present a generative autoencoder that provides fast encoding, faithful reconstructions (eg. retaining the identity of a face), sharp generated/reconstructed samples in high resolutions, and a well-structured latent space that supports semantic manipulation of the inputs. There are no current autoencoder or GAN models that satisfactorily achieve all of these. We build on the progressively growing autoencoder model PIONEER, for which we completely alter the training dynamics based on a careful analysis of recently introduced normalization schemes. We show significantly improved visual and qua…
Learning a disentangled, interpretable, and structured latent representation in 3D generative models of faces and bodies is still an open problem. The problem is particularly acute when control over identity features is required. In this paper, we propose an intuitive yet effective self-supervised approach to train a 3D shape variational autoencoder (VAE) which encourages a disentangled latent representation of identity features. Curating the mini-batch generation by swapping arbitrary features across different shapes allows to define a loss function leveraging known differences and similariti…
We investigate the potential of fusing human examiner decisions for the task of digital face manipulation detection. To this end, various decision fusion methods are proposed incorporating the examiners' decision confidence, experience level, and their time to take a decision. Conducted experiments are based on a psychophysical evaluation of digital face image manipulation detection capabilities of humans in which different manipulation techniques were applied, i.e. face morphing, face swapping and retouching. The decisions of 223 participants were fused to simulate crowds of up to seven human…
In this paper, we present an approach based on reinforcement learning for eye tracking data manipulation. It is based on two opposing agents, where one tries to classify the data correctly and the second agent looks for patterns in the data, which get manipulated to hide specific information. We show that our approach is successfully applicable to preserve the privacy of the subjects. For this purpose, we evaluate our approach iteratively to showcase the behavior of the reinforcement learning based approach. In addition, we evaluate the importance of temporal, as well as spatial, information o…
Recent advances in autoencoders and generative models have given rise to effective video forgery methods, used for generating so-called "deepfakes". Mitigation research is mostly focused on post-factum deepfake detection and not on prevention. We complement these efforts by introducing a novel class of adversarial attacks---training-resistant attacks---which can disrupt face-swapping autoencoders whether or not its adversarial images have been included in the training set of said autoencoders. We propose the Oscillating GAN (OGAN) attack, a novel attack optimized to be training-resistant, whic…
University of Maryland（马里兰大学）；Adobe Research（Adobe研究院）
As tools for content editing mature, and artificial intelligence (AI) based algorithms for synthesizing media grow, the presence of manipulated content across online media is increasing. This phenomenon causes the spread of misinformation, creating a greater need to distinguish between ``real'' and ``manipulated'' content. To this end, we present VideoSham, a dataset consisting of 826 videos (413 real and 413 manipulated). Many of the existing deepfake datasets focus exclusively on two types of facial manipulations -- swapping with a different subject's face or altering the existing face. Vide…
A*STAR Institute of High Performance Computing (IHPC)（新加坡科技研究局高性能计算研究所）；A*STAR Institute of Information Research (IR)（新加坡科技研究局信息研究所）；National University of Singapore (NUS)（新加坡国立大学）；Alibaba DAMO Academy（阿里巴巴达摩院）
We present an end-to-end Reinforcement Learning(RL) framework for robotic manipulation tasks, using a robust and efficient keypoints representation. The proposed method learns keypoints from camera images as the state representation, through a self-supervised autoencoder architecture. The keypoints encode the geometric information, as well as the relationship of the tool and target in a compact representation to ensure efficient and robust learning. After keypoints learning, the RL step then learns the robot motion from the extracted keypoints state representation. The keypoints and RL learnin…
Institute for Infocomm Research (IR), A*STAR（A*STAR资讯通信研究院（IR））；Institute for High Performance Computing (IHPC), A*STAR（A*STAR高性能计算研究院（IHPC））
We present KOVIS, a novel learning-based, calibration-free visual servoing method for fine robotic manipulation tasks with eye-in-hand stereo camera system. We train the deep neural network only in the simulated environment; and the trained model could be directly used for real-world visual servoing tasks. KOVIS consists of two networks. The first keypoint network learns the keypoint representation from the image using with an autoencoder. Then the visual servoing network learns the motion based on keypoints extracted from the camera image. The two networks are trained end-to-end in the simula…
IBM Research - Tokyo, IBM Japan（IBM日本东京研究院）；LeapMind Inc.（LeapMind公司）
Robotic learning in simulation environments provides a faster, more scalable, and safer training methodology than learning directly with physical robots. Also, synthesizing images in a simulation environment for collecting large-scale image data is easy, whereas capturing camera images in the real world is time consuming and expensive. However, learning from only synthetic images may not achieve the desired performance in real environments due to the gap between synthetic and real images. We thus propose a method that transfers learned capability of detecting object position from a simulation …
Stony Brook University（石溪大学）；Newark Beth Israel Medical Center（纽瓦克贝斯以色列医疗中心）；University Hospitals Cleveland Medical Center（克利夫兰大学医院医疗中心）
Well-labeled datasets of chest radiographs (CXRs) are difficult to acquire due to the high cost of annotation. Thus, it is desirable to learn a robust and transferable representation in an unsupervised manner to benefit tasks that lack labeled data. Unlike natural images, medical images have their own domain prior; e.g., we observe that many pulmonary diseases, such as the COVID-19, manifest as changes in the lung tissue texture rather than the anatomical structure. Therefore, we hypothesize that studying only the texture without the influence of structure variations would be advantageous for …
Robust Identity Perceptual Watermark Against Deepfake Face Swapping
School of Computing, National University of Singapore（新加坡国立大学计算机学院）；Shandong Artificial Intelligence Institute, Qilu University of Technology (Shandong Academy of Sciences)（山东人工智能研究院，齐鲁工业大学（山东科学院））；School of Cyber Security, Qilu University of Technology (Shandong Academy of Sciences)（齐鲁工业大学（山东科学院）网络安全学院）；Key Laboratory of Computing Power Network and Information Security, Ministry of Education, China（教育部计算能力网络与信息安全重点实验室）
Disruptive Attacks on Face Swapping via Low-Frequency Perceptual Perturbations
Department of Mathematics and Artificial Intelligence（数学与人工智能系）；Shandong Artificial Intelligence Institute（山东省人工智能研究所）；Qilu University of Technology（齐鲁大学）
Regularized autoencoders learn the latent codes, a structure with the regularization under the distribution, which enables them the capability to infer the latent codes given observations and generate new samples given the codes. However, they are sometimes ambiguous as they tend to produce reconstructions that are not necessarily faithful reproduction of the inputs. The main reason is to enforce the learned latent code distribution to match a prior distribution while the true distribution remains unknown. To improve the reconstruction quality and learn the latent space a manifold structure, t…
Istanbul Technical University（伊斯坦布尔理工大学）；Halmstad University（哈尔姆斯塔德大学）
Despite decades of research, understanding human manipulation activities is, and has always been, one of the most attractive and challenging research topics in computer vision and robotics. Recognition and prediction of observed human manipulation actions have their roots in the applications related to, for instance, human-robot interaction and robot learning from demonstration. The current research trend heavily relies on advanced convolutional neural networks to process the structured Euclidean data, such as RGB camera images. These networks, however, come with immense computational complexi…
Autoencoder networks are unsupervised approaches aiming at combining generative and representational properties by learning simultaneously an encoder-generator map. Although studied extensively, the issues of whether they have the same generative power of GANs, or learn disentangled representations, have not been fully addressed. We introduce an autoencoder that tackles these issues jointly, which we call Adversarial Latent Autoencoder (ALAE). It is a general architecture that can leverage recent improvements on GAN training procedures. We designed two autoencoders: one based on a MLP encoder,…
DeepFake face swapping presents a significant threat to online security and social media, which can replace the source face in an arbitrary photo/video with the target face of an entirely different person. In order to prevent this fraud, some researchers have begun to study the adversarial methods against DeepFake or face manipulation. However, existing works focus on the white-box setting or the black-box setting driven by abundant queries, which severely limits the practical application of these methods. To tackle this problem, we introduce a practical adversarial attack that does not requir…
The task of face attribute manipulation has found increasing applications, but still remains challenging with the requirement of editing the attributes of a face image while preserving its unique details. In this paper, we choose to combine the Variational AutoEncoder (VAE) and Generative Adversarial Network (GAN) for photorealistic image generation. We propose an effective method to modify a modest amount of pixels in the feature maps of an encoder, changing the attribute strength continuously without hindering global information. Our training objectives of VAE and GAN are reinforced by the s…
University of Toronto（多伦多大学）；Vector Institute（向量研究所）
Variational autoencoders (VAEs) are widely used deep generative models capable of learning unsupervised latent representations of data. Such representations are often difficult to interpret or control. We consider the problem of unsupervised learning of features correlated to specific labels in a dataset. We propose a VAE-based generative model which we show is capable of extracting features correlated to binary labels in the data and structuring it in a latent subspace which is easy to interpret. Our model, the Conditional Subspace VAE (CSVAE), uses mutual information minimization to learn a …
In recent years, increasing deployment of face recognition technology in security-critical settings, such as border control or law enforcement, has led to considerable interest in the vulnerability of face recognition systems to attacks utilising legitimate documents, which are issued on the basis of digitally manipulated face images. As automated manipulation and attack detection remains a challenging task, conventional processes with human inspectors performing identity verification remain indispensable. These circumstances merit a closer investigation of human capabilities in detecting mani…
We introduce a novel generative autoencoder network model that learns to encode and reconstruct images with high quality and resolution, and supports smooth random sampling from the latent space of the encoder. Generative adversarial networks (GANs) are known for their ability to simulate random high-quality images, but they cannot reconstruct existing images. Previous works have attempted to extend GANs to support such inference but, so far, have not delivered satisfactory high-quality results. Instead, we propose the Progressively Growing Generative Autoencoder (PIONEER) network which achiev…
Diffusion probabilistic models (DPMs) have achieved remarkable quality in image generation that rivals GANs'. But unlike GANs, DPMs use a set of latent variables that lack semantic meaning and cannot serve as a useful representation for other tasks. This paper explores the possibility of using DPMs for representation learning and seeks to extract a meaningful and decodable representation of an input image via autoencoding. Our key idea is to use a learnable encoder for discovering the high-level semantics, and a DPM as the decoder for modeling the remaining stochastic variations. Our method ca…
Nanyang Technological University（南洋理工大学）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）
Generative adversarial networks (GANs) have achieved great success in image translation and manipulation. However, high-fidelity image generation with faithful style control remains a grand challenge in computer vision. This paper presents a versatile image translation and manipulation framework that achieves accurate semantic and style guidance in image generation by explicitly building a correspondence. To handle the quadratic complexity incurred by building the dense correspondences, we introduce a bi-level feature alignment strategy that adopts a top-$k$ operation to rank block-wise featur…
Stony Brook University（石溪大学）；CentraleSupélec（高等电力学院）；INRIA（法国国家信息与自动化研究所）；Therapanacea；University College London（伦敦大学学院）；Facebook AI Research（Facebook人工智能研究院）
In this work we introduce Deforming Autoencoders, a generative model for images that disentangles shape from appearance in an unsupervised manner. As in the deformable template paradigm, shape is represented as a deformation between a canonical coordinate system (`template') and an observed image, while appearance is modeled in `canonical', template, coordinates, thus discarding variability due to deformations. We introduce novel techniques that allow this approach to be deployed in the setting of autoencoders and show that this method can be used for unsupervised group-wise image alignment. W…
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…
Shenzhen University（深圳大学）；University of Nottingham（诺丁汉大学）
We present a new method for improving the performances of variational autoencoder (VAE). In addition to enforcing the deep feature consistent principle thus ensuring the VAE output and its corresponding input images to have similar deep features, we also implement a generative adversarial training mechanism to force the VAE to output realistic and natural images. We present experimental results to show that the VAE trained with our new method outperforms state of the art in generating face images with much clearer and more natural noses, eyes, teeth, hair textures as well as reasonable backgro…
The Hong Kong University of Science and Technology（香港科技大学）
We propose SinIR, an efficient reconstruction-based framework trained on a single natural image for general image manipulation, including super-resolution, editing, harmonization, paint-to-image, photo-realistic style transfer, and artistic style transfer. We train our model on a single image with cascaded multi-scale learning, where each network at each scale is responsible for image reconstruction. This reconstruction objective greatly reduces the complexity and running time of training, compared to the GAN objective. However, the reconstruction objective also exacerbates the output quality.…
CentraleSupélec（中央理工-高等电力学院）；Stony Brook University（石溪大学）；The Alan Turing Institute（艾伦·图灵研究所）；UCL（伦敦大学学院）；Ariel AI；Imperial College（帝国理工学院）
In this work we introduce Lifting Autoencoders, a generative 3D surface-based model of object categories. We bring together ideas from non-rigid structure from motion, image formation, and morphable models to learn a controllable, geometric model of 3D categories in an entirely unsupervised manner from an unstructured set of images. We exploit the 3D geometric nature of our model and use normal information to disentangle appearance into illumination, shading and albedo. We further use weak supervision to disentangle the non-rigid shape variability of human faces into identity and expression. W…
Counterfactual Explanations for Medical Image Classification and Regression using Diffusion Autoencoder
Technical University of Munich（慕尼黑工业大学）；Klinikum rechts der Isar（右侧伊萨尔医院）；Institute for Artificial Intelligence and Computer Science in Medicine, Technical University of Munich（慕尼黑工业大学人工智能与医学计算机科学研究所）；Computer Aided Medical Procedures, Technical University of Munich（慕尼黑工业大学计算机辅助医疗程序研究所）；AI for Image-Guided Diagnosis and Therapy, Technical University of Munich（慕尼黑工业大学图像引导诊断与治疗人工智能研究所）
A Deep Learning Approach for Facial Attribute Manipulation and Reconstruction in Surveillance and Reconnaissance
Department of Networks and Digital Media（网络与数字媒体系）；Kingston University（金史密斯大学）；School of Computer Science and Engineering（计算机科学与工程学院）；University of Westminster（威斯敏斯特大学）
We propose a visualization technique that utilizes neural network embeddings and a generative network to reconstruct original data. This method allows for independent manipulation of individual image embeddings through its non-parametric structure, providing more flexibility than traditional autoencoder approaches. We have evaluated the effectiveness of this technique in data visualization and compared it to t-SNE and VAE methods. Furthermore, we have demonstrated the scalability of our method through visualizations on the ImageNet dataset. Our technique has potential applications in human-in-…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；The Chinese University of Hong Kong（香港中文大学）；Google Inc.（谷歌公司）
High-level manipulation of facial expressions in images --- such as changing a smile to a neutral expression --- is challenging because facial expression changes are highly non-linear, and vary depending on the appearance of the face. We present a fully automatic approach to editing faces that combines the advantages of flow-based face manipulation with the more recent generative capabilities of Variational Autoencoders (VAEs). During training, our model learns to encode the flow from one expression to another over a low-dimensional latent space. At test time, expression editing can be done si…
Latent Diffusion Autoencoders: Toward Efficient and Meaningful Unsupervised Representation Learning in Medical Imaging
Department of Electrical and Information Engineering (DIEI), University of Cassino and Southern Lazio（电气与信息工程系（DIEI），卡斯诺和南部拉齐亚大学）；Diagnostic Image Analysis Group, Radboud University Medical Center（影像诊断分析组，拉德堡德大学医学中心）；Department of Medical Imaging, Radboud University Medical Center（医学成像系，拉德堡德大学医学中心）
San Diego State University（圣地亚哥州立大学）；University of California San Diego（加州大学圣地亚哥分校）
Deepfakes and manipulated media are becoming a prominent threat due to the recent advances in realistic image and video synthesis techniques. There have been several attempts at combating Deepfakes using machine learning classifiers. However, such classifiers do not generalize well to black-box image synthesis techniques and have been shown to be vulnerable to adversarial examples. To address these challenges, we introduce a deep learning based semi-fragile watermarking technique that allows media authentication by verifying an invisible secret message embedded in the image pixels. Instead of …
Indian Institute of Technology Madras（印度理工学院马德拉斯分校）
The success of Deep Generative Models at high-resolution image generation has led to their extensive utilization for style editing of real images. Most existing methods work on the principle of inverting real images onto their latent space, followed by determining controllable directions. Both inversion of real images and determination of controllable latent directions are computationally expensive operations. Moreover, the determination of controllable latent directions requires additional human supervision. This work aims to explore the efficacy of mask-guided feature modulation in the laten…
