Variational Capsules for Image Analysis and Synthesis
School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Center for Research on Intelligent Perception and Computing, CASIA（中国科学院自动化研究所智能感知与计算研究中心）；National Laboratory of Pattern Recognition, CASIA（中国科学院自动化研究所模式识别国家重点实验室）；Center for Excellence in Brain Science and Intelligence Technology, CAS（中国科学院脑科学与智能技术卓越创新中心）
Huaibo Huang, Lingxiao Song, Ran He, Zhenan Sun, Tieniu Tan
A capsule is a group of neurons whose activity vector models different properties of the same entity. This paper extends the capsule to a generative version, named variational capsules (VCs). Each VC produces a latent variable for a specific entity, making it possible to integrate image analysis and image synthesis into a unified framework. Variational capsules model an image as a composition of entities in a probabilistic model. Different capsules' divergence with a specific prior distribution represents the presence of different entities, which can be applied in image analysis tasks such as classification. In addition, variational capsules encode multiple entities in a semantically-disentangling way. Diverse instantiations of capsules are related to various properties of the same entity, making it easy to generate diverse samples with fine-grained semantic attributes. Extensive experiments demonstrate that deep networks designed with variational capsules can not only achieve promising performance on image analysis tasks (including image classification and attribute prediction) but can also improve the diversity and controllability of image synthesis.
University of Sydney（悉尼大学）；University of New South Wales（新南威尔士大学）
Micro-expressions are reflections of people's true feelings and motives, which attract an increasing number of researchers into the study of automatic facial micro-expression recognition. The short detection window, the subtle facial muscle movements, and the limited training samples make micro-expression recognition challenging. To this end, we propose a novel Identity-aware and Capsule-Enhanced Generative Adversarial Network with graph-based reasoning (ICE-GAN), introducing micro-expression synthesis as an auxiliary task to assist recognition. The generator produces synthetic faces with cont…
In this paper, we propose Generative Adversarial Network (GAN) architectures that use Capsule Networks for image-synthesis. Based on the principal of positional-equivariance of features, Capsule Network's ability to encode spatial relationships between the features of the image helps it become a more powerful critic in comparison to Convolutional Neural Networks (CNNs) used in current architectures for image synthesis. Our proposed GAN architectures learn the data manifold much faster and therefore, synthesize visually accurate images in significantly lesser number of training samples and trai…
Semantic Map Guided Synthesis of Wireless Capsule Endoscopy Images using Diffusion Models
Captos Co., Ltd.（Captos株式会社）；Seoreu Co., Ltd.（Seoreu株式会社）；Pusan National University School of Medicine（釜山大学医学院）；Pusan National University Yangsan Hospital（釜山大学梁山医院）；Kyungpook National University（庆北大学）
Clinical Evaluation of Medical Image Synthesis: A Case Study in Wireless Capsule Endoscopy
University of Thessaly（塞萨利大学）；University of Southern Denmark（南丹麦大学）；Pomeranian Medical University（波美拉尼亚医科大学）；Clínica Universidad de Navarra（纳瓦拉大学临床医院）；Mater Dei Hospital（马特尔迪医院）；University of Parma（帕尔马大学）；Hospital Clínic i Provincial de Barcelona（巴塞罗那临床医院）；Centro de Investigación Biomédica en Red de Enfermedades Hepáticas y Digestivas（肝病和消化系统疾病生物医学研究网络中心）；Royal Infirmary of Edinburgh（爱丁堡皇家医院）；University Hospitals of Leicester NHS Trust（莱斯特大学医院NHS信托基金）；Hospital da Senhora da Oliveira - Guimarães（吉马良斯圣母奥利维拉医院）；Lund University（隆德大学）；Skåne University Hospital（斯科讷大学医院）
We propose a novel capsule network based variational encoder architecture, called Bayesian capsules (B-Caps), to modulate the mean and standard deviation of the sampling distribution in the latent space. We hypothesized that this approach can learn a better representation of features in the latent space than traditional approaches. Our hypothesis was tested by using the learned latent variables for image reconstruction task, where for MNIST and Fashion-MNIST datasets, different classes were separated successfully in the latent space using our proposed model. Our experimental results have shown…
Shanghai Key Laboratory of Multidimensional Information Processing（上海市多维度信息处理重点实验室）；Key Laboratory of Advanced Theory and Application in Statistics & Data Science, East China Normal University（华东师范大学统计与数据科学前沿理论及应用重点实验室）
Novel view synthesis often needs the paired data from both the source and target views. This paper proposes a view translation model under cVAE-GAN framework without requiring the paired data. We design a conditional deformable module (CDM) which uses the view condition vectors as the filters to convolve the feature maps of the main branch in VAE. It generates several pairs of displacement maps to deform the features, like the 2D optical flows. The results are fed into the deformed feature based normalization module (DFNM), which scales and offsets the main branch feature, given its deformed o…
Capsule networks are a recently proposed type of neural network shown to outperform alternatives in challenging shape recognition tasks. In capsule networks, scalar neurons are replaced with capsule vectors or matrices, whose entries represent different properties of objects. The relationships between objects and their parts are learned via trainable viewpoint-invariant transformation matrices, and the presence of a given object is decided by the level of agreement among votes from its parts. This interaction occurs between capsule layers and is a process called routing-by-agreement. In this p…
University of Bonn（波恩大学）；National University of Singapore（新加坡国立大学）
Hand image synthesis and pose estimation from RGB images are both highly challenging tasks due to the large discrepancy between factors of variation ranging from image background content to camera viewpoint. To better analyze these factors of variation, we propose the use of disentangled representations and a disentangled variational autoencoder (dVAE) that allows for specific sampling and inference of these factors. The derived objective from the variational lower bound as well as the proposed training strategy are highly flexible, allowing us to handle cross-modal encoders and decoders as we…
Illinois Institute of Technology（伊利诺伊理工学院）；Wuhan University（武汉大学）；Snap Inc.（Snap公司）
Diffusion probabilistic models (DPMs) have become a popular approach to conditional generation, due to their promising results and support for cross-modal synthesis. A key desideratum in conditional synthesis is to achieve high correspondence between the conditioning input and generated output. Most existing methods learn such relationships implicitly, by incorporating the prior into the variational lower bound. In this work, we take a different route -- we explicitly enhance input-output connections by maximizing their mutual information. To this end, we introduce a Conditional Discrete Contr…
In this paper, we present a characteristic extraction algorithm and the Multi-domain Image Characteristics Dataset of characteristic-tagged images to simulate the way a human brain classifies cross-domain information and generates insight. The intent was to identify prominent characteristics in data and use this identification mechanism to auto-generate insight from data in other unseen domains. An information extraction algorithm is proposed which is a combination of Variational Autoencoders (VAEs) and Capsule Networks. Capsule Networks are used to decompose images into their individual featu…
University of Padova（帕多瓦大学）；National University of Defense Technology（国防科技大学）
In open set recognition, a classifier has to detect unknown classes that are not known at training time. In order to recognize new categories, the classifier has to project the input samples of known classes in very compact and separated regions of the features space for discriminating samples of unknown classes. Recently proposed Capsule Networks have shown to outperform alternatives in many fields, particularly in image recognition, however they have not been fully applied yet to open-set recognition. In capsule networks, scalar neurons are replaced by capsule vectors or matrices, whose entr…
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）；Amazon（亚马逊）
Deep generative models have achieved conspicuous progress in realistic image synthesis with multifarious conditional inputs, while generating diverse yet high-fidelity images remains a grand challenge in conditional image generation. This paper presents a versatile framework for conditional image generation which incorporates the inductive bias of CNNs and powerful sequence modeling of auto-regression that naturally leads to diverse image generation. Instead of independently quantizing the features of multiple domains as in prior research, we design an integrated quantization scheme with a var…
From Baseline to Follow-Up: Counterfactual Spine DXA Image Synthesis in UK Biobank Using a Causal Hierarchical Variational Autoencoder
School of Electronics and Computer Science（电子与计算机科学学院）；University of Southampton（萨塞克斯大学）；MRC Lifecourse Epidemiology Centre（英国医学研究理事会生命周期流行病学中心）；University of Southampton, Southampton General Hospital（萨塞克斯大学索马塞特医院）；Computer Science University of Southampton（计算机科学萨塞克斯大学）
Institute of Digital Technologies, Loughborough University（拉夫堡大学数字技术研究所）
Synthesizing a realistic image from textual description is a major challenge in computer vision. Current text to image synthesis approaches falls short of producing a highresolution image that represent a text descriptor. Most existing studies rely either on Generative Adversarial Networks (GANs) or Variational Auto Encoders (VAEs). GANs has the capability to produce sharper images but lacks the diversity of outputs, whereas VAEs are good at producing a diverse range of outputs, but the images generated are often blurred. Taking into account the relative advantages of both GANs and VAEs, we pr…
Rutgers, The State University of New Jersey（罗格斯大学新泽西州立大学）；Rutgers University（罗格斯大学）
Automatic synthesis of faces from visual attributes is an important problem in computer vision and has wide applications in law enforcement and entertainment. With the advent of deep generative convolutional neural networks (CNNs), attempts have been made to synthesize face images from attributes and text descriptions. In this paper, we take a different approach, where we formulate the original problem as a stage-wise learning problem. We first synthesize the facial sketch corresponding to the visual attributes and then we reconstruct the face image based on the synthesized sketch. The propose…
Xi'an Jiaotong University（西安交通大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
Fog and haze are weathers with low visibility which are adversarial to the driving safety of intelligent vehicles equipped with optical sensors like cameras and LiDARs. Therefore image dehazing for perception enhancement and haze image synthesis for testing perception abilities are equivalently important in the development of such autonomous driving systems. From the view of image translation, these two problems are essentially dual with each other, which have the potentiality to be solved jointly. In this paper, we propose an unsupervised Image-to-Image Translation framework based on Variatio…
Heidelberg Collaboratory for Image Processing（海德堡图像处理合作实验室）；IWR Heidelberg University（海德堡大学跨学科科学计算中心）
Generating and representing human behavior are of major importance for various computer vision applications. Commonly, human video synthesis represents behavior as sequences of postures while directly predicting their likely progressions or merely changing the appearance of the depicted persons, thus not being able to exercise control over their actual behavior during the synthesis process. In contrast, controlled behavior synthesis and transfer across individuals requires a deep understanding of body dynamics and calls for a representation of behavior that is independent of appearance and als…
Heidelberg Collaboratory for Image Processing（海德堡图像处理协作实验室）；IWR, Heidelberg University, Germany（德国海德堡大学IWR研究所（注：根据机构粒度要求，提取到大学级别，此处IWR为海德堡大学下属研究机构，整体保留原机构名及大学级别信息））
Deep generative models have demonstrated great performance in image synthesis. However, results deteriorate in case of spatial deformations, since they generate images of objects directly, rather than modeling the intricate interplay of their inherent shape and appearance. We present a conditional U-Net for shape-guided image generation, conditioned on the output of a variational autoencoder for appearance. The approach is trained end-to-end on images, without requiring samples of the same object with varying pose or appearance. Experiments show that the model enables conditional image generat…
University of Southern California（南加州大学）；IIIT（印度德里英迪拉·甘地信息技术学院（德里印度信息技术学院））；IIT（印度理工学院）
An interpretable generative model for handwritten digits synthesis is proposed in this work. Modern image generative models, such as Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs), are trained by backpropagation (BP). The training process is complex and the underlying mechanism is difficult to explain. We propose an interpretable multi-stage PCA method to achieve the same goal and use handwritten digit images synthesis as an illustrative example. First, we derive principal-component-analysis-based (PCA-based) transform kernels at each stage based on the covariance o…
University of Chinese Academy of Sciences（中国科学院大学）；Center for Research on Intelligent Perception and Computing, CASIA（中国科学院自动化研究所智能感知与计算研究中心）；National Laboratory of Pattern Recognition, CASIA（中国科学院自动化研究所模式识别国家重点实验室）；Center for Excellence in Brain Science and Intelligence Technology, CAS（中国科学院脑科学与智能技术卓越创新中心）
We present a novel introspective variational autoencoder (IntroVAE) model for synthesizing high-resolution photographic images. IntroVAE is capable of self-evaluating the quality of its generated samples and improving itself accordingly. Its inference and generator models are jointly trained in an introspective way. On one hand, the generator is required to reconstruct the input images from the noisy outputs of the inference model as normal VAEs. On the other hand, the inference model is encouraged to classify between the generated and real samples while the generator tries to fool it as GANs.…
Amazon Development Centre Scotland（亚马逊苏格兰开发中心）；University of Edinburgh（爱丁堡大学）；The Alan Turing Institute（艾伦·图灵研究所）
Capsule networks (see e.g. Hinton et al., 2018) aim to encode knowledge of and reason about the relationship between an object and its parts. In this paper we specify a generative model for such data, and derive a variational algorithm for inferring the transformation of each model object in a scene, and the assignments of observed parts to the objects. We derive a learning algorithm for the object models, based on variational expectation maximization (Jordan et al., 1999). We also study an alternative inference algorithm based on the RANSAC method of Fischler and Bolles (1981). We apply these…
Southern University of Science and Technology（南方科技大学）；Technical University of Munich（慕尼黑工业大学）；University of Zurich（苏黎世大学）
Medical image synthesis has attracted increasing attention because it could generate missing image data, improving diagnosis and benefits many downstream tasks. However, so far the developed synthesis model is not adaptive to unseen data distribution that presents domain shift, limiting its applicability in clinical routine. This work focuses on exploring domain adaptation (DA) of 3D image-to-image synthesis models. First, we highlight the technical difference in DA between classification, segmentation and synthesis models. Second, we present a novel efficient adaptation approach based on 2D v…
Semantic image synthesis is a process for generating photorealistic images from a single semantic mask. To enrich the diversity of multimodal image synthesis, previous methods have controlled the global appearance of an output image by learning a single latent space. However, a single latent code is often insufficient for capturing various object styles because object appearance depends on multiple factors. To handle individual factors that determine object styles, we propose a class- and layer-wise extension to the variational autoencoder (VAE) framework that allows flexible control over each…
We present fast, realistic image generation on high-resolution, multimodal datasets using hierarchical variational autoencoders (VAEs) trained on a deterministic autoencoder's latent space. In this two-stage setup, the autoencoder compresses the image into its semantic features, which are then modeled with a deep VAE. With this method, the VAE avoids modeling the fine-grained details that constitute the majority of the image's code length, allowing it to focus on learning its structural components. We demonstrate the effectiveness of our two-stage approach, achieving a FID of 9.34 on the Image…
University of California, Merced（加利福尼亚大学默塞德分校）；National Tsing Hua University（台湾清华大学）；Google Research（谷歌研究院）
Flexible user controls are desirable for content creation and image editing. A semantic map is commonly used intermediate representation for conditional image generation. Compared to the operation on raw RGB pixels, the semantic map enables simpler user modification. In this work, we specifically target at generating semantic maps given a label-set consisting of desired categories. The proposed framework, SegVAE, synthesizes semantic maps in an iterative manner using conditional variational autoencoder. Quantitative and qualitative experiments demonstrate that the proposed model can generate r…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
We present an empirical evaluation of fMRI data augmentation via synthesis. For synthesis we use generative mod-els trained on real neuroimaging data to produce novel task-dependent functional brain images. Analyzed generative mod-els include classic approaches such as the Gaussian mixture model (GMM), and modern implicit generative models such as the generative adversarial network (GAN) and the variational auto-encoder (VAE). In particular, the proposed GAN and VAE models utilize 3-dimensional convolutions, which enables modeling of high-dimensional brain image tensors with structured spatial…
The Pennsylvania State University（宾夕法尼亚州立大学）；Tsinghua University（清华大学）；Google Brain（谷歌大脑）；Facebook（脸书）
In many applications of computer graphics, art and design, it is desirable for a user to provide intuitive non-image input, such as text, sketch, stroke, graph or layout, and have a computer system automatically generate photo-realistic images that adhere to the input content. While classic works that allow such automatic image content generation have followed a framework of image retrieval and composition, recent advances in deep generative models such as generative adversarial networks (GANs), variational autoencoders (VAEs), and flow-based methods have enabled more powerful and versatile im…
We propose a recurrent variational auto-encoder for texture synthesis. A novel loss function, FLTBNK, is used for training the texture synthesizer. It is rotational and partially color invariant loss function. Unlike L2 loss, FLTBNK explicitly models the correlation of color intensity between pixels. Our texture synthesizer generates neighboring tiles to expand a sample texture and is evaluated using various texture patterns from Describable Textures Dataset (DTD). We perform both quantitative and qualitative experiments with various loss functions to evaluate the performance of our proposed l…
One of the consequences of climate change is anobserved increase in the frequency of extreme cli-mate events. That poses a challenge for weatherforecast and generation algorithms, which learnfrom historical data but should embed an often un-certain bias to create correct scenarios. This paperinvestigates how mapping climate data to a knowndistribution using variational autoencoders mighthelp explore such biases and control the synthesisof weather fields towards more extreme climatescenarios. We experimented using a monsoon-affected precipitation dataset from southwest In-dia, which should give…
Centre de mathématiques et de leurs applications（数学及其应用中心）；CNRS（法国国家科学研究中心）；ENS Paris-Saclay（巴黎萨克雷高等师范学院）；Université Paris-Saclay（巴黎萨克雷大学）；Institut Denis Poisson（德尼·泊松研究所）；Université d’Orléans（奥尔良大学）；Université de Tours（图尔大学）；Univ. Bordeaux（波尔多大学）；IMB（波尔多数学研究所）；Bordeaux INP（波尔多国立理工学院）
Recent years have seen the rise of convolutional neural network techniques in exemplar-based image synthesis. These methods often rely on the minimization of some variational formulation on the image space for which the minimizers are assumed to be the solutions of the synthesis problem. In this paper we investigate, both theoretically and experimentally, another framework to deal with this problem using an alternate sampling/minimization scheme. First, we use results from information geometry to assess that our method yields a probability measure which has maximum entropy under some constrain…
We consider the problem of synthesizing multi-action human motion sequences of arbitrary lengths. Existing approaches have mastered motion sequence generation in single action scenarios, but fail to generalize to multi-action and arbitrary-length sequences. We fill this gap by proposing a novel efficient approach that leverages expressiveness of Recurrent Transformers and generative richness of conditional Variational Autoencoders. The proposed iterative approach is able to generate smooth and realistic human motion sequences with an arbitrary number of actions and frames while doing so in lin…
Harvard University（哈佛大学）；Facebook AI（脸书人工智能）；Carnegie Mellon University（卡内基梅隆大学）；The Hong Kong Polytechnic University（香港理工大学）；Université de Montréal（蒙特利尔大学）；Nanjing University of Information Science and Technology（南京信息工程大学）；Fanhan Tech. Inc.（泛函科技有限公司）
This paper targets on learning-based novel view synthesis from a single or limited 2D images without the pose supervision. In the viewer-centered coordinates, we construct an end-to-end trainable conditional variational framework to disentangle the unsupervisely learned relative-pose/rotation and implicit global 3D representation (shape, texture and the origin of viewer-centered coordinates, etc.). The global appearance of the 3D object is given by several appearance-describing images taken from any number of viewpoints. Our spatial correlation module extracts a global 3D representation from t…
MRI-to-CT Synthesis With Cranial Suture Segmentations Using A Variational Autoencoder Framework
Sheikh Zayed Institute for Pediatric Surgical Innovation, Children’s National Hospital, Washington, DC, USA（Sheikh Zayed儿童外科创新研究所，Children’s National医院，华盛顿特区，美国）；CIBORG Lab, Department of Radiology, Children’s Hospital Los Angeles, Los Angeles, CA, USA（CIBORG实验室，放射科，Children’s Hospital Los Angeles，洛杉矶，加利福尼亚州，美国）；Departments of Radiology and Biomedical Engineering, University of Southern California, Los Angeles, CA, USA（放射科和生物医学工程系，美国南加州大学，洛杉矶，加利福尼亚州，美国）；School of Medicine and Health Sciences, George Washington University, Washington, DC, USA（医学与健康科学学院，乔治华盛顿大学，华盛顿特区，美国）
University of Florida（佛罗里达大学）；Georgia State University（佐治亚州立大学）
Generating multi-contrasts/modal MRI of the same anatomy enriches diagnostic information but is limited in practice due to excessive data acquisition time. In this paper, we propose a novel deep-learning model for joint reconstruction and synthesis of multi-modal MRI using incomplete k-space data of several source modalities as inputs. The output of our model includes reconstructed images of the source modalities and high-quality image synthesized in the target modality. Our proposed model is formulated as a variational problem that leverages several learnable modality-specific feature extract…
King’s College London（伦敦国王学院）；National Hospital for Neurology and Neurosurgery（国家神经内科和神经外科医院）；Thomas Jefferson University（托马斯·杰斐逊大学）；University of Washington（华盛顿大学）
Laser interstitial thermal therapy (LITT) is a novel minimally invasive treatment that is used to ablate intracranial structures to treat mesial temporal lobe epilepsy (MTLE). Region of interest (ROI) segmentation before and after LITT would enable automated lesion quantification to objectively assess treatment efficacy. Deep learning techniques, such as convolutional neural networks (CNNs) are state-of-the-art solutions for ROI segmentation, but require large amounts of annotated data during the training. However, collecting large datasets from emerging treatments such as LITT is impractical.…
This dissertation is devoted to provide advanced nonconvex nonsmooth variational models of (Magnetic Resonance Image) MRI reconstruction, efficient learnable image reconstruction algorithms and parameter training algorithms that improve the accuracy and robustness of the optimization-based deep learning methods for compressed sensing MRI reconstruction and synthesis. The first part introduces a novel optimization based deep neural network whose architecture is inspired by proximal gradient descent for solving a variational model. The second part is a substantial extension of the preliminary wo…
Unified Cross-Modal Medical Image Synthesis with Hierarchical Mixture of Product-of-Experts
Harvard Medical School and the Brigham and Women’s Hospital（哈佛医学院和布里洛妇产科医院）；MIND Team, Inria Saclay, Université Paris-Saclay, Palaiseau, France and Sorbonne Université, Institut du Cerveau - Paris Brain Institute - ICM, CNRS, Inria, Inserm, AP-HP, Hôpital de la Pitié Salpêtrière（MIND团队、Inria Saclay、巴黎萨克雷大学、Palaiseau，法国以及索邦大学、巴黎脑研究所-ICM、CNRS、Inria、Inserm、AP-HP、皮蒂埃萨勒普蒂耶医院）；Massachusetts Institute of Technology（麻省理工学院）
Federal University of Santa Catarina (UFSC)（圣卡塔琳娜联邦大学）
Variational AutoEncoders (VAE) employ deep learning models to learn a continuous latent z-space that is subjacent to a high-dimensional observed dataset. With that, many tasks are made possible, including face reconstruction and face synthesis. In this work, we investigated how face masks can help the training of VAEs for face reconstruction, by restricting the learning to the pixels selected by the face mask. An evaluation of the proposal using the celebA dataset shows that the reconstructed images are enhanced with the face masks, especially when SSIM loss is used either with l1 or l2 loss f…
University of Amsterdam（阿姆斯特丹大学）；Vrije Universiteit Amsterdam（阿姆斯特丹自由大学）；BrainCreators B.V.（BrainCreators公司）
The framework of variational autoencoders (VAEs) provides a principled method for jointly learning latent-variable models and corresponding inference models. However, the main drawback of this approach is the blurriness of the generated images. Some studies link this effect to the objective function, namely, the (negative) log-likelihood. Here, we propose to enhance VAEs by adding a random variable that is a downscaled version of the original image and still use the log-likelihood function as the learning objective. Further, by providing the downscaled image as an input to the decoder, it can …
