Data-driven approaches for modeling human skeletal motion have found various applications in interactive media and social robotics. Challenges remain in these fields for generating high-fidelity samples and robustly reconstructing motion from imperfect input data, due to e.g. missed marker detection. In this paper, we propose a probabilistic generative model to synthesize and reconstruct long horizon motion sequences conditioned on past information and control signals, such as the path along which an individual is moving. Our method adapts the existing work MoGlow by introducing a new graph-based model. The model leverages the spatial-temporal graph convolutional network (ST-GCN) to effectively capture the spatial structure and temporal correlation of skeletal motion data at multiple scales. We evaluate the models on a mixture of motion capture datasets of human locomotion with foot-step and bone-length analysis. The results demonstrate the advantages of our model in reconstructing missing markers and achieving comparable results on generating realistic future poses. When the inputs are imperfect, our model shows improvements on robustness of generation.
fortiss GmbH, Research Institute of the Free State of Bavaria（巴伐利亚自由州研究机构fortiss有限公司）；Technical University of Munich（慕尼黑工业大学）
The future motion of traffic participants is inherently uncertain. To plan safely, therefore, an autonomous agent must take into account multiple possible trajectory outcomes and prioritize them. Recently, this problem has been addressed with generative neural networks. However, most generative models either do not learn the true underlying trajectory distribution reliably, or do not allow predictions to be associated with likelihoods. In our work, we model motion prediction directly as a density estimation problem with a normalizing flow between a noise distribution and the future motion dist…
Georgia Institute of Technology（佐治亚理工学院）；Rice University（莱斯大学）；University Medical Center Utrecht（乌得勒支大学医学中心）；Centrum Wiskunde & Informatica（荷兰数学与计算机科学研究院）
We present a novel approach to transcranial ultrasound computed tomography that utilizes normalizing flows to improve the speed of imaging and provide Bayesian uncertainty quantification. Our method combines physics-informed methods and data-driven methods to accelerate the reconstruction of the final image. We make use of a physics-informed summary statistic to incorporate the known ultrasound physics with the goal of compressing large incoming observations. This compression enables efficient training of the normalizing flow and standardizes the size of the data regardless of imaging configur…
University of Southern California（南加州大学）；Argonne National Laboratory（阿贡国家实验室）
Ptychography, as an essential tool for high-resolution and nondestructive material characterization, presents a challenging large-scale nonlinear and non-convex inverse problem; however, its intrinsic photon statistics create clear opportunities for statistical-based deep learning approaches to tackle these challenges, which has been underexplored. In this work, we explore normalizing flows to obtain a surrogate for the high-dimensional posterior, which also enables the characterization of the uncertainty associated with the reconstruction: an extremely desirable capability when judging the re…
McGill University（麦吉尔大学）；Mila（米拉研究所）；University of Toronto（多伦多大学）；Vector Institute（向量研究所）
The choice of approximate posterior distributions plays a central role in stochastic variational inference (SVI). One effective solution is the use of normalizing flows \cut{defined on Euclidean spaces} to construct flexible posterior distributions. However, one key limitation of existing normalizing flows is that they are restricted to the Euclidean space and are ill-equipped to model data with an underlying hierarchical structure. To address this fundamental limitation, we present the first extension of normalizing flows to hyperbolic spaces. We first elevate normalizing flows to hyperbolic …
Variational Autoencoder with Normalizing flow for X-ray spectral fitting
Department of Physics & Astronomy University of Southampton（物理与天文学系 英国南安普顿大学）；Laboratoire d’astrophysique EPFL（天体物理学实验室 EPFL）；Harvard-Smithsonian Center for Astrophysics（哈佛-史密松天体物理中心）
University of California at Berkeley（加州大学伯克利分校）；International Computer Science Institute（国际计算机科学研究所）；University of Queensland（昆士兰大学）
We introduce stochastic normalizing flows, an extension of continuous normalizing flows for maximum likelihood estimation and variational inference (VI) using stochastic differential equations (SDEs). Using the theory of rough paths, the underlying Brownian motion is treated as a latent variable and approximated, enabling efficient training of neural SDEs as random neural ordinary differential equations. These SDEs can be used for constructing efficient Markov chains to sample from the underlying distribution of a given dataset. Furthermore, by considering families of targeted SDEs with prescr…
Unifying supervised learning and VAEs -- coverage, systematics and goodness-of-fit in normalizing-flow based neural network models for astro-particle reconstructions
Helmholtz-Zentrum Dresden-Rossendorf（亥姆霍兹德累斯顿罗森多夫研究中心）；European XFEL（欧洲X射线自由电子激光器）；University of Siegen（锡根大学）；Forschungszentrum Jülich（于利希研究中心）
Grazing-Incidence Small-Angle X-ray Scattering (GISAXS) is a modern imaging technique used in material research to study nanoscale materials. Reconstruction of the parameters of an imaged object imposes an ill-posed inverse problem that is further complicated when only an in-plane GISAXS signal is available. Traditionally used inference algorithms such as Approximate Bayesian Computation (ABC) rely on computationally expensive scattering simulation software, rendering analysis highly time-consuming. We propose a simulation-based framework that combines variational auto-encoders and normalizing…
TrajFlow: A Generative Framework for Occupancy Density Estimation Using Normalizing Flows
Department of Computer Science University of Minnesota（计算机科学系明尼苏达大学）；Department of Civil Environmental and Geo- Engineering University of Minnesota（土木环境与地球工程系明尼苏达大学）
We study a normalizing flow in the latent space of a top-down generator model, in which the normalizing flow model plays the role of the informative prior model of the generator. We propose to jointly learn the latent space normalizing flow prior model and the top-down generator model by a Markov chain Monte Carlo (MCMC)-based maximum likelihood algorithm, where a short-run Langevin sampling from the intractable posterior distribution is performed to infer the latent variables for each observed example, so that the parameters of the normalizing flow prior and the generator can be updated with …
National Yang Ming Chiao Tung University（国立阳明交通大学）；CNIT（意大利国家电信联盟）；University of Brescia（布雷西亚大学）
This paper presents an end-to-end learning-based video compression system, termed CANF-VC, based on conditional augmented normalizing flows (CANF). Most learned video compression systems adopt the same hybrid-based coding architecture as the traditional codecs. Recent research on conditional coding has shown the sub-optimality of the hybrid-based coding and opens up opportunities for deep generative models to take a key role in creating new coding frameworks. CANF-VC represents a new attempt that leverages the conditional ANF to learn a video generative model for conditional inter-frame coding…
VAN-AD: Visual Masked Autoencoder with Normalizing Flow For Time Series Anomaly Detection
School of Computer Science (National Pilot Software Engineering School)（计算机学院（国家级试点软件工程学院））；Beijing University of Posts and Telecommunications（北京邮电大学）；China Telecom Research Institute Beijing（中国电信研究院北京）；Department of Computer Science, Missouri University of Science and Technology（计算机科学系，密苏里科技大学）
Computing excited states of molecules using normalizing flows
Center for Free-Electron Laser Science CFEL, Deutsches Elektronen-Synchrotron DESY（自由电子激光科学中心 CFEL，德意志电子同步辐射研究中心）；Department of Chemistry, Universität Hamburg（汉堡大学化学系）；Center for Ultrafast Imaging, Universität Hamburg（超快成像中心，汉堡大学）；Department of Physics, Universität Hamburg（汉堡大学物理系）；Department of Mathematics, Universität Hamburg（汉堡大学数学系）
MPI Informatics（马克斯·普朗克信息学研究所）；Saarland Informatics Campus（萨尔兰信息学园区）；Google Inc（谷歌公司）；University of Bonn（波恩大学）；Universidad Rey Juan Carlos（胡安卡洛斯国王大学）；University of Freiburg（弗莱堡大学）
Reconstructing two-hand interactions from a single image is a challenging problem due to ambiguities that stem from projective geometry and heavy occlusions. Existing methods are designed to estimate only a single pose, despite the fact that there exist other valid reconstructions that fit the image evidence equally well. In this paper we propose to address this issue by explicitly modeling the distribution of plausible reconstructions in a conditional normalizing flow framework. This allows us to directly supervise the posterior distribution through a novel determinant magnitude regularizatio…
ETH Zurich（苏黎世联邦理工学院）；University of Bologna（博洛尼亚大学）；Google（谷歌）；TU Munich（慕尼黑工业大学）
Recently normalizing flows (NFs) have demonstrated state-of-the-art performance on modeling 3D point clouds while allowing sampling with arbitrary resolution at inference time. However, these flow-based models still require long training times and large models for representing complicated geometries. This work enhances their representational power by applying mixtures of NFs to point clouds. We show that in this more general framework each component learns to specialize in a particular subregion of an object in a completely unsupervised fashion. By instantiating each mixture component with a c…
Monocular 3D human pose and shape estimation is challenging due to the many degrees of freedom of the human body and thedifficulty to acquire training data for large-scale supervised learning in complex visual scenes. In this paper we present practical semi-supervised and self-supervised models that support training and good generalization in real-world images and video. Our formulation is based on kinematic latent normalizing flow representations and dynamics, as well as differentiable, semantic body part alignment loss functions that support self-supervised learning. In extensive experiments…
IRCAM（声学与音乐研究与协作所）；CNRS（法国国家科学研究中心）；Sorbonne Université（索邦大学）；Laboratorio d’Informatica Musicale (LIM)（音乐信息学实验室）；UNIMI（米兰大学）
The ubiquity of sound synthesizers has reshaped music production and even entirely defined new music genres. However, the increasing complexity and number of parameters in modern synthesizers make them harder to master. Hence, the development of methods allowing to easily create and explore with synthesizers is a crucial need. Here, we introduce a novel formulation of audio synthesizer control. We formalize it as finding an organized latent audio space that represents the capabilities of a synthesizer, while constructing an invertible mapping to the space of its parameters. By using this formu…
Information Technology University (ITU)-Punjab（旁遮普信息技术大学（ITU））；University of Southern Queensland（南昆士兰大学）
Multishot Magnetic Resonance Imaging (MRI) is a promising imaging modality that can produce a high-resolution image with relatively less data acquisition time. The downside of multishot MRI is that it is very sensitive to subject motion and even small amounts of motion during the scan can produce artifacts in the final MR image that may cause misdiagnosis. Numerous efforts have been made to address this issue; however, all of these proposals are limited in terms of how much motion they can correct and the required computational time. In this paper, we propose a novel generative networks based …
ReFlow: Self-correction Motion Learning for Dynamic Scene Reconstruction
University of Science and Technology of China（中国科学技术大学）；National Key Laboratory of Deep Space Exploration, Deep Space Exploration Laboratory（深空探测实验室，深空探测全国重点实验室）
Berkeley Center for Cosmological Physics（伯克利宇宙物理中心）；University of California（加利福尼亚大学）；Lawrence Berkeley National Laboratory（劳伦斯伯克利国家实验室）
Principal Component Analysis (PCA) minimizes the reconstruction error given a class of linear models of fixed component dimensionality. Probabilistic PCA adds a probabilistic structure by learning the probability distribution of the PCA latent space weights, thus creating a generative model. Autoencoders (AE) minimize the reconstruction error in a class of nonlinear models of fixed latent space dimensionality and outperform PCA at fixed dimensionality. Here, we introduce the Probabilistic Autoencoder (PAE) that learns the probability distribution of the AE latent space weights using a normaliz…
Discovering Antagonists in Networks of Systems: Robot Deployment
Institute of Engineering and Computational Mechanics, University of Stuttgart（工程与计算力学研究所，斯图加特大学）；Department of Mechanical Engineering, LUT University（机械工程系，卢托大学）
Unsupervised Low-dose CT Reconstruction with One-way Conditional Normalizing Flows
School of Mathematical Sciences, Capital Normal University（首都师范大学数学学院）；Centre for Mathematical Imaging Techniques, University of Liverpool（利物浦大学数学成像技术中心）；Department of Mathematics and Statistics, University of Strathclyde（斯特拉思克莱德大学数学与统计学系）
ETH Zürich（苏黎世联邦理工学院）；Meta Reality Labs Research（Meta现实实验室）；University of Surrey（萨里大学）
Neural face avatars that are trained from multi-view data captured in camera domes can produce photo-realistic 3D reconstructions. However, at inference time, they must be driven by limited inputs such as partial views recorded by headset-mounted cameras or a front-facing camera, and sparse facial landmarks. To mitigate this asymmetry, we introduce a prior model that is conditioned on the runtime inputs and tie this prior space to the 3D face model via a normalizing flow in the latent space. Our proposed model, LiP-Flow, consists of two encoders that learn representations from the rich trainin…
South China University of Technology（华南理工大学）；City University of Hong Kong（香港城市大学）；Tsinghua University（清华大学）；Nanyang Technological University（南洋理工大学）
Point cloud upsampling aims to generate dense point clouds from given sparse ones, which is a challenging task due to the irregular and unordered nature of point sets. To address this issue, we present a novel deep learning-based model, called PU-Flow, which incorporates normalizing flows and weight prediction techniques to produce dense points uniformly distributed on the underlying surface. Specifically, we exploit the invertible characteristics of normalizing flows to transform points between Euclidean and latent spaces and formulate the upsampling process as ensemble of neighbouring points…
In contemporary society, surveillance anomaly detection, i.e., spotting anomalous events such as crimes or accidents in surveillance videos, is a critical task. As anomalies occur rarely, most training data consists of unlabeled videos without anomalous events, which makes the task challenging. Most existing methods use an autoencoder (AE) to learn to reconstruct normal videos; they then detect anomalies based on their failure to reconstruct the appearance of abnormal scenes. However, because anomalies are distinguished by appearance as well as motion, many previous approaches have explicitly …
Sun Yat-sen University（中山大学）；Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education（机器智能与先进计算教育部重点实验室）
Despite the great progress in video understanding made by deep convolutional neural networks, feature representation learned by existing methods may be biased to static visual cues. To address this issue, we propose a novel method to suppress static visual cues (SSVC) based on probabilistic analysis for self-supervised video representation learning. In our method, video frames are first encoded to obtain latent variables under standard normal distribution via normalizing flows. By modelling static factors in a video as a random variable, the conditional distribution of each latent variable bec…
Fast light-field 3D microscopy with out-of-distribution detection and adaptation through Conditional Normalizing Flows
Technical University of Munich（慕尼黑工业大学）；Munich Institute of Biomedical Engineering（慕尼黑生物医学工程研究所）；Massachusetts Institute of Technology（麻省理工学院）；University of Bern（伯尔尼大学）
Human pose estimation from single images is a challenging problem that is typically solved by supervised learning. Unfortunately, labeled training data does not yet exist for many human activities since 3D annotation requires dedicated motion capture systems. Therefore, we propose an unsupervised approach that learns to predict a 3D human pose from a single image while only being trained with 2D pose data, which can be crowd-sourced and is already widely available. To this end, we estimate the 3D pose that is most likely over random projections, with the likelihood estimated using normalizing …
ETH Zurich（苏黎世联邦理工学院）；Google（谷歌）；Technical University Munich（慕尼黑工业大学）
Normalizing Flows (NFs) are flexible explicit generative models that have been shown to accurately model complex real-world data distributions. However, their invertibility constraint imposes limitations on data distributions that reside on lower dimensional manifolds embedded in higher dimensional space. Practically, this shortcoming is often bypassed by adding noise to the data which impacts the quality of the generated samples. In contrast to prior work, we approach this problem by generating samples from the original data distribution given full knowledge about the perturbed distribution a…
Nanyang Technological University（南洋理工大学）；City University of Hong Kong（香港城市大学）
To enhance low-light images to normally-exposed ones is highly ill-posed, namely that the mapping relationship between them is one-to-many. Previous works based on the pixel-wise reconstruction losses and deterministic processes fail to capture the complex conditional distribution of normally exposed images, which results in improper brightness, residual noise, and artifacts. In this paper, we investigate to model this one-to-many relationship via a proposed normalizing flow model. An invertible network that takes the low-light images/features as the condition and learns to map the distributio…
Enhancing Low-resolution Image Representation Through Normalizing Flows
Yau Mathematical Sciences Center, Tsinghua University, Beijing, China（清华大学数学科学中心，北京，中国）；Beijing Institute of Mathematical Sciences and Applications, Beijing, China（北京数学科学研究院，北京，中国）；Department of Mathematics, National University of Singapore, Singapore（新加坡国立大学数学系，新加坡）；Department of Pharmaceutical Chemistry, University of California, San Francisco, CA, USA（加州大学旧金山分校药学化学系，美国，加利福尼亚州，旧金山）；Yau Mathematical Sciences Center and Department of Mathematical Sciences, Tsinghua University, Beijing, China（清华大学数学科学中心及数学系，北京，中国）
