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 well as semi-supervised learning scenarios. Experiments show that our dVAE can synthesize highly realistic images of the hand specifiable by both pose and image background content and also estimate 3D hand poses from RGB images with accuracy competitive with state-of-the-art on two public benchmarks.
VAE requires the standard Gaussian distribution as a prior in the latent space. Since all codes tend to follow the same prior, it often suffers the so-called "posterior collapse". To avoid this, this paper introduces the class specific distribution for the latent code. But different from CVAE, we present a method for disentangling the latent space into the label relevant and irrelevant dimensions, $\bm{\mathrm{z}}_s$ and $\bm{\mathrm{z}}_u$, for a single input. We apply two separated encoders to map the input into $\bm{\mathrm{z}}_s$ and $\bm{\mathrm{z}}_u$ respectively, and then give the conc…
Pengcheng Laboratory（鹏城实验室）；Shenzhen University（深圳大学）；University of Nottingham（诺丁汉大学）
Facial attributes in StyleGAN generated images are entangled in the latent space which makes it very difficult to independently control a specific attribute without affecting the others. Supervised attribute editing requires annotated training data which is difficult to obtain and limits the editable attributes to those with labels. Therefore, unsupervised attribute editing in an disentangled latent space is key to performing neat and versatile semantic face editing. In this paper, we present a new technique termed Structure-Texture Independent Architecture with Weight Decomposition and Orthog…
Heidelberg Collaboratory for Image Processing（海德堡图像处理合作实验室）；Heidelberg University（海德堡大学）
Deep generative models come with the promise to learn an explainable representation for visual objects that allows image sampling, synthesis, and selective modification. The main challenge is to learn to properly model the independent latent characteristics of an object, especially its appearance and pose. We present a novel approach that learns disentangled representations of these characteristics and explains them individually. Training requires only pairs of images depicting the same object appearance, but no pose annotations. We propose an additional classifier that estimates the minimal a…
Sorbonne Université（索邦大学）；CNRS（法国国家科学研究中心）；Conservatoire National des Arts et Métiers（法国国立工艺学院）
In computer vision, disentangling techniques aim at improving latent representations of images by modeling factors of variation. In this paper, we propose DualDis, a new auto-encoder-based framework that disentangles and linearizes class and attribute information. This is achieved thanks to a two-branch architecture forcing the separation of the two kinds of information, accompanied by a decoder for image reconstruction and generation. To effectively separate the information, we propose to use a combination of regular and adversarial classifiers to guide the two branches in specializing for cl…
Heidelberg Collaboratory for Image Processing（海德堡图像处理合作实验室）；Heidelberg University（海德堡大学）
Neural networks have greatly boosted performance in computer vision by learning powerful representations of input data. The drawback of end-to-end training for maximal overall performance are black-box models whose hidden representations are lacking interpretability: Since distributed coding is optimal for latent layers to improve their robustness, attributing meaning to parts of a hidden feature vector or to individual neurons is hindered. We formulate interpretation as a translation of hidden representations onto semantic concepts that are comprehensible to the user. The mapping between both…
National Laboratory of Pattern Recognition, CASIA（模式识别国家重点实验室，中国科学院自动化研究所）；Center for Research on Intelligent Perception and Computing, CASIA（智能感知与计算研究中心，中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Face completion aims to generate semantically new pixels for missing facial components. It is a challenging generative task due to large variations of face appearance. This paper studies generative face completion under structured occlusions. We treat the face completion and corruption as disentangling and fusing processes of clean faces and occlusions, and propose a jointly disentangling and fusing Generative Adversarial Network (DF-GAN). First, three domains are constructed, corresponding to the distributions of occluded faces, clean faces and structured occlusions. The disentangling and fus…
Exploring the potential of GANs for unsupervised disentanglement learning, this paper proposes a novel GAN-based disentanglement framework with One-Hot Sampling and Orthogonal Regularization (OOGAN). While previous works mostly attempt to tackle disentanglement learning through VAE and seek to implicitly minimize the Total Correlation (TC) objective with various sorts of approximation methods, we show that GANs have a natural advantage in disentangling with an alternating latent variable (noise) sampling method that is straightforward and robust. Furthermore, we provide a brand-new perspective…
Traditional face editing methods often require a number of sophisticated and task specific algorithms to be applied one after the other --- a process that is tedious, fragile, and computationally intensive. In this paper, we propose an end-to-end generative adversarial network that infers a face-specific disentangled representation of intrinsic face properties, including shape (i.e. normals), albedo, and lighting, and an alpha matte. We show that this network can be trained on "in-the-wild" images by incorporating an in-network physically-based image formation module and appropriate loss funct…
In the last few years there have been important advancements in generative models with the two dominant approaches being Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs). However, standard Autoencoders (AEs) and closely related structures have remained popular because they are easy to train and adapt to different tasks. An interesting question is if we can achieve state-of-the-art performance with AEs while retaining their good properties. We propose an answer to this question by introducing a new model called Y-Autoencoder (Y-AE). The structure and training procedure…
Autonomous Vision Group（自主视觉小组）；MPI for Intelligent Systems（马克斯·普朗克智能系统研究所）；University of Tübingen（蒂宾根大学）
While 2D generative adversarial networks have enabled high-resolution image synthesis, they largely lack an understanding of the 3D world and the image formation process. Thus, they do not provide precise control over camera viewpoint or object pose. To address this problem, several recent approaches leverage intermediate voxel-based representations in combination with differentiable rendering. However, existing methods either produce low image resolution or fall short in disentangling camera and scene properties, e.g., the object identity may vary with the viewpoint. In this paper, we propose…
Disentangling factors of variation has become a very challenging problem on representation learning. Existing algorithms suffer from many limitations, such as unpredictable disentangling factors, poor quality of generated images from encodings, lack of identity information, etc. In this paper, we propose a supervised learning model called DNA-GAN which tries to disentangle different factors or attributes of images. The latent representations of images are DNA-like, in which each individual piece (of the encoding) represents an independent factor of the variation. By annihilating the recessive …
In this work we present an adversarial training algorithm that exploits correlations in video to learn --without supervision-- an image generator model with a disentangled latent space. The proposed methodology requires only a few modifications to the standard algorithm of Generative Adversarial Networks (GAN) and involves training with sets of frames taken from short videos. We train our model over two datasets of face-centered videos which present different people speaking or moving the head: VidTIMIT and YouTube Faces datasets. We found that our proposal allows us to split the generator lat…
Large intra-class variation is the result of changes in multiple object characteristics. Images, however, only show the superposition of different variable factors such as appearance or shape. Therefore, learning to disentangle and represent these different characteristics poses a great challenge, especially in the unsupervised case. Moreover, large object articulation calls for a flexible part-based model. We present an unsupervised approach for disentangling appearance and shape by learning parts consistently over all instances of a category. Our model for learning an object representation i…
Bosch Center for AI（博世人工智能中心）；MPI for Informatics（马克斯·普朗克信息学研究所）；University of Tübingen（图宾根大学）
Prior work has extensively studied the latent space structure of GANs for unconditional image synthesis, enabling global editing of generated images by the unsupervised discovery of interpretable latent directions. However, the discovery of latent directions for conditional GANs for semantic image synthesis (SIS) has remained unexplored. In this work, we specifically focus on addressing this gap. We propose a novel optimization method for finding spatially disentangled class-specific directions in the latent space of pretrained SIS models. We show that the latent directions found by our method…
In this work, we propose and validate a framework to leverage language-image pretraining representations for training-free zero-shot sketch-to-image synthesis. We show that disentangled content and style representations can be utilized to guide image generators to employ them as sketch-to-image generators without (re-)training any parameters. Our approach for disentangling style and content entails a simple method consisting of elementary arithmetic assuming compositionality of information in representations of input sketches. Our results demonstrate that this approach is competitive with stat…
We study the problem of building models that disentangle independent factors of variation. Such models could be used to encode features that can efficiently be used for classification and to transfer attributes between different images in image synthesis. As data we use a weakly labeled training set. Our weak labels indicate what single factor has changed between two data samples, although the relative value of the change is unknown. This labeling is of particular interest as it may be readily available without annotation costs. To make use of weak labels we introduce an autoencoder model and …
Inria（法国国家信息与自动化研究所）；Université Côte d’Azur（蔚蓝海岸大学）；University of Warsaw（华沙大学）
Creating realistic human videos entails the challenge of being able to simultaneously generate both appearance, as well as motion. To tackle this challenge, we introduce G$^{3}$AN, a novel spatio-temporal generative model, which seeks to capture the distribution of high dimensional video data and to model appearance and motion in disentangled manner. The latter is achieved by decomposing appearance and motion in a three-stream Generator, where the main stream aims to model spatio-temporal consistency, whereas the two auxiliary streams augment the main stream with multi-scale appearance and mot…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
The state-of-the-art StyleGAN2 network supports powerful methods to create and edit art, including generating random images, finding images "like" some query, and modifying content or style. Further, recent advancements enable training with small datasets. We apply these methods to synthesize card art, by training on a novel Yu-Gi-Oh dataset. While noise inputs to StyleGAN2 are essential for good synthesis, we find that coarse-scale noise interferes with latent variables on this dataset because both control long-scale image effects. We observe over-aggressive variation in art with changes in n…
Ludwig Maximilian University of Munich（慕尼黑大学）；Heidelberg University（海德堡大学）；Runway ML（Runway ML公司）
By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond. Additionally, their formulation allows for a guiding mechanism to control the image generation process without retraining. However, since these models typically operate directly in pixel space, optimization of powerful DMs often consumes hundreds of GPU days and inference is expensive due to sequential evaluations. To enable DM training on limited computational resources while retaining their quality and …
Suzhou University of Science and Technology（苏州科技大学）；Tianjin University（天津大学）；Suzhou Institute of Trade & Commerce（苏州经贸职业技术学院）；Xi’an Jiaotong-Liverpool University（西交利物浦大学）
Using generative models to synthesize visual features from semantic distribution is one of the most popular solutions to ZSL image classification in recent years. The triplet loss (TL) is popularly used to generate realistic visual distributions from semantics by automatically searching discriminative representations. However, the traditional TL cannot search reliable unseen disentangled representations due to the unavailability of unseen classes in ZSL. To alleviate this drawback, we propose in this work a multi-modal triplet loss (MMTL) which utilizes multimodal information to search a disen…
Beijing University of Technology（北京工业大学）；Louisiana State University（路易斯安那州立大学）；Dalian University of Technology（大连理工大学）
This paper presents a new Text-to-Image generation model, named Distribution Regularization Generative Adversarial Network (DR-GAN), to generate images from text descriptions from improved distribution learning. In DR-GAN, we introduce two novel modules: a Semantic Disentangling Module (SDM) and a Distribution Normalization Module (DNM). SDM combines the spatial self-attention mechanism and a new Semantic Disentangling Loss (SDL) to help the generator distill key semantic information for the image generation. DNM uses a Variational Auto-Encoder (VAE) to normalize and denoise the image latent d…
Conditional generative adversarial networks (cGANs) target at synthesizing diverse images given the input conditions and latent codes, but unfortunately, they usually suffer from the issue of mode collapse. To solve this issue, previous works mainly focused on encouraging the correlation between the latent codes and their generated images, while ignoring the relations between images generated from various latent codes. The recent MSGAN tried to encourage the diversity of the generated image but only considers "negative" relations between the image pairs. In this paper, we propose a novel DivCo…
NEC Laboratories America（NEC美国实验室）；University of Rochester（罗切斯特大学）
Although progress has been made for text-to-image synthesis, previous methods fall short of generalizing to unseen or underrepresented attribute compositions in the input text. Lacking compositionality could have severe implications for robustness and fairness, e.g., inability to synthesize the face images of underrepresented demographic groups. In this paper, we introduce a new framework, StyleT2I, to improve the compositionality of text-to-image synthesis. Specifically, we propose a CLIP-guided Contrastive Loss to better distinguish different compositions among different sentences. To furthe…
University of Science and Technology Beijing（北京科技大学）；DAMO Academy, Alibaba Group（阿里巴巴集团达摩院）
Manipulating latent code in generative adversarial networks (GANs) for facial image synthesis mainly focuses on continuous attribute synthesis (e.g., age, pose and emotion), while discrete attribute synthesis (like face mask and eyeglasses) receives less attention. Directly applying existing works to facial discrete attributes may cause inaccurate results. In this work, we propose an innovative framework to tackle challenging facial discrete attribute synthesis via semantic decomposing, dubbed SD-GAN. To be concrete, we explicitly decompose the discrete attribute representation into two compon…
We present LARNet, a novel end-to-end approach for generating human action videos. A joint generative modeling of appearance and dynamics to synthesize a video is very challenging and therefore recent works in video synthesis have proposed to decompose these two factors. However, these methods require a driving video to model the video dynamics. In this work, we propose a generative approach instead, which explicitly learns action dynamics in latent space avoiding the need of a driving video during inference. The generated action dynamics is integrated with the appearance using a recurrent hie…
This paper investigates an open research task of text-to-image synthesis for automatically generating or manipulating images from text descriptions. Prevailing methods mainly use the text as conditions for GAN generation, and train different models for the text-guided image generation and manipulation tasks. In this paper, we propose a novel unified framework of Cycle-consistent Inverse GAN (CI-GAN) for both text-to-image generation and text-guided image manipulation tasks. Specifically, we first train a GAN model without text input, aiming to generate images with high diversity and quality. T…
In this paper, we present an approach for combining non-rigid structure-from-motion (NRSfM) with deep generative models,and propose an efficient framework for discovering trajectories in the latent space of 2D GANs corresponding to changes in 3D geometry. Our approach uses recent advances in NRSfM and enables editing of the camera and non-rigid shape information associated with the latent codes without needing to retrain the generator. This formulation provides an implicit dense 3D reconstruction as it enables the image synthesis of novel shapes from arbitrary view angles and non-rigid structu…
University of Dundee（邓迪大学）；University of Cambridge（剑桥大学）；University of Bath（巴斯大学）；East China Normal University（华东师范大学）
MRI synthesis promises to mitigate the challenge of missing MRI modality in clinical practice. Diffusion model has emerged as an effective technique for image synthesis by modelling complex and variable data distributions. However, most diffusion-based MRI synthesis models are using a single modality. As they operate in the original image domain, they are memory-intensive and less feasible for multi-modal synthesis. Moreover, they often fail to preserve the anatomical structure in MRI. Further, balancing the multiple conditions from multi-modal MRI inputs is crucial for multi-modal synthesis. …
University of Tübingen（图宾根大学）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）
Semantic image synthesis enables control over unconditional image generation by allowing guidance on what is being generated. We conditionally synthesize the latent space from a vector quantized model (VQ-model) pre-trained to autoencode images. Instead of training an autoregressive Transformer on separately learned conditioning latents and image latents, we find that jointly learning the conditioning and image latents significantly improves the modeling capabilities of the Transformer model. While our jointly trained VQ-model achieves a similar reconstruction performance to a vanilla VQ-model…
Image editing using a pretrained StyleGAN generator has emerged as a powerful paradigm for facial editing, providing disentangled controls over age, expression, illumination, etc. However, the approach cannot be directly adopted for video manipulations. We hypothesize that the main missing ingredient is the lack of fine-grained and disentangled control over face location, face pose, and local facial expressions. In this work, we demonstrate that such a fine-grained control is indeed achievable using pretrained StyleGAN by working across multiple (latent) spaces (namely, the positional space, t…
DiffSynth: Latent In-Iteration Deflickering for Realistic Video Synthesis
School of Data Science and Engineering, East China Normal University（华东师范大学数据科学与工程学院）；School of Information, Xiamen University（厦门大学信息学院）；Alibaba Group（阿里巴巴集团）
We present a simple neural rendering architecture that helps variational autoencoders (VAEs) learn disentangled representations. Instead of the deconvolutional network typically used in the decoder of VAEs, we tile (broadcast) the latent vector across space, concatenate fixed X- and Y-"coordinate" channels, and apply a fully convolutional network with 1x1 stride. This provides an architectural prior for dissociating positional from non-positional features in the latent distribution of VAEs, yet without providing any explicit supervision to this effect. We show that this architecture, which we …
University of Copenhagen（哥本哈根大学）；Rigshospitalet（哥本哈根大学国立医院）
Medical imaging plays a vital role in modern diagnostics and treatment. The temporal nature of disease or treatment progression often results in longitudinal data. Due to the cost and potential harm, acquiring large medical datasets necessary for deep learning can be difficult. Medical image synthesis could help mitigate this problem. However, until now, the availability of GANs capable of synthesizing longitudinal volumetric data has been limited. To address this, we use the recent advances in latent space-based image editing to propose a novel joint learning scheme to explicitly embed tempor…
LMU Munich（慕尼黑大学）；University Hospital, LMU Munich（慕尼黑大学附属医院）；Munich Center for Machine Learning（慕尼黑机器学习中心）
While recent advances in large-scale foundational models show promising results, their application to the medical domain has not yet been explored in detail. In this paper, we progress into the realms of large-scale modeling in medical synthesis by proposing Cheff - a foundational cascaded latent diffusion model, which generates highly-realistic chest radiographs providing state-of-the-art quality on a 1-megapixel scale. We further propose MaCheX, which is a unified interface for public chest datasets and forms the largest open collection of chest X-rays up to date. With Cheff conditioned on r…
Investigating Data Memorization in 3D Latent Diffusion Models for Medical Image Synthesis
Heidelberg University Hospital（海德堡大学医院）；German Centre for Cardiovascular Research（德国心血管研究中心）；Heidelberg University（海德堡大学）；University Medical Center Mannheim（曼海姆大学医学中心）
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…
Make-A-Volume: Leveraging Latent Diffusion Models for Cross-Modality 3D Brain MRI Synthesis
The University of Hong Kong（香港大学）；The Chinese University of Hong Kong（香港中文大学）；Qilu Hospital of Shandong University（山东大学齐鲁医院）；Nanyang Technological University（南洋理工大学）
Indian Institute of Technology Madras（印度理工学院马德拉斯分校）
With the advent of an increasing number of Augmented and Virtual Reality applications that aim to perform meaningful and controlled style edits on images of human faces, the impetus for the task of parsing face images to produce accurate and fine-grained semantic segmentation maps is more than ever before. Few State of the Art (SOTA) methods which solve this problem, do so by incorporating priors with respect to facial structure or other face attributes such as expression and pose in their deep classifier architecture. Our endeavour in this work is to do away with the priors and complex pre-pr…
Generative models that learn disentangled representations for different factors of variation in an image can be very useful for targeted data augmentation. By sampling from the disentangled latent subspace of interest, we can efficiently generate new data necessary for a particular task. Learning disentangled representations is a challenging problem, especially when certain factors of variation are difficult to label. In this paper, we introduce a novel architecture that disentangles the latent space into two complementary subspaces by using only weak supervision in form of pairwise similarity…
Deep learning models obtain impressive accuracy in road scenes understanding, however they need a large quantity of labeled samples for their training. Additionally, such models do not generalise well to environments where the statistical properties of data do not perfectly match those of training scenes, and this can be a significant problem for intelligent vehicles. Hence, domain adaptation approaches have been introduced to transfer knowledge acquired on a label-abundant source domain to a related label-scarce target domain. In this work, we design and carefully analyse multiple latent spac…
University of Toronto（多伦多大学）；Samsung Toronto AI Research Center（三星多伦多人工智能研究中心）；Vector Institute for Artificial Intelligence（矢量人工智能研究所）
A complete representation of 3D objects requires characterizing the space of deformations in an interpretable manner, from articulations of a single instance to changes in shape across categories. In this work, we improve on a prior generative model of geometric disentanglement for 3D shapes, wherein the space of object geometry is factorized into rigid orientation, non-rigid pose, and intrinsic shape. The resulting model can be trained from raw 3D shapes, without correspondences, labels, or even rigid alignment, using a combination of classical spectral geometry and probabilistic disentanglem…
A variational autoencoder (VAE) is a probabilistic machine learning framework for posterior inference that projects an input set of high-dimensional data to a lower-dimensional, latent space. The latent space learned with a VAE offers exciting opportunities to develop new data-driven design processes in creative disciplines, in particular, to automate the generation of multiple novel designs that are aesthetically reminiscent of the input data but that were unseen during training. However, the learned latent space is typically disorganized and entangled: traversing the latent space along a sin…
We present StyleFusion, a new mapping architecture for StyleGAN, which takes as input a number of latent codes and fuses them into a single style code. Inserting the resulting style code into a pre-trained StyleGAN generator results in a single harmonized image in which each semantic region is controlled by one of the input latent codes. Effectively, StyleFusion yields a disentangled representation of the image, providing fine-grained control over each region of the generated image. Moreover, to help facilitate global control over the generated image, a special input latent code is incorporate…
Massachusetts Institute of Technology（麻省理工学院）；New York Structural Biology Center（纽约结构生物学中心）
Given an image dataset, we are often interested in finding data generative factors that encode semantic content independently from pose variables such as rotation and translation. However, current disentanglement approaches do not impose any specific structure on the learned latent representations. We propose a method for explicitly disentangling image rotation and translation from other unstructured latent factors in a variational autoencoder (VAE) framework. By formulating the generative model as a function of the spatial coordinate, we make the reconstruction error differentiable with respe…
Disentangling Latent Embeddings with Sparse Linear Concept Subspaces (SLiCS)
Department of Electrical & Computer Engineering, University of Delaware, USA（电气与计算机工程系，德雷克塞尔大学）；Naval Surface Warfare Center, Panama City Division, Panama City, Florida, USA（Panama City 分部，海军水面 warfare 中心）；Department of Navy award N00014-24-1-2259 issued by the Office of Naval Research（海军部奖项 N00014-24-1-2259，由海军研究办公室颁发）；Department of Computer & Information Sciences, University of Delaware, USA（计算机与信息科学系，德雷克塞尔大学）
