Adapting motion to new contexts in digital entertainment often demands fast agile prototyping. State-of-the-art techniques use reinforcement learning policies for simulating the underlined motion in a physics engine. Unfortunately, policies typically fail on unseen tasks and it is too time-consuming to fine-tune the policy for every new morphological, environmental, or motion change. We propose a novel point of view on using policy networks as a representation of motion for physics-based character animation. Our policies are compact, tailored to individual motion tasks, and preserve similarity with nearby tasks. This allows us to view the space of all motions as a manifold of policies where sampling substitutes training. We obtain memory-efficient encoding of motion that leverages the characteristics of control policies such as being generative, and robust to small environmental changes. With this perspective, we can sample novel motions by directly manipulating weights and biases through a Diffusion Model. Our newly generated policies can adapt to previously unseen characters, potentially saving time in rapid prototyping scenarios. Our contributions include the introduction of Common Neighbor Policy regularization to constrain policy similarity during motion imitation training making them suitable for generative modeling; a Diffusion Model adaptation for diverse morphology; and an open policy dataset. The results show that we can learn non-linear transformations in the policy space from labeled examples, and conditionally generate new ones. In a matter of seconds, we sample a batch of policies for different conditions that show comparable motion fidelity metrics as their respective trained ones.

The increasing prevalence of non-alcoholic fatty liver disease (NAFLD) has caused public concern in recent years. The high prevalence and risk of severe complications make monitoring NAFLD progression a public health priority. Fibrosis staging from liver biopsy images plays a key role in demonstrating the histological progression of NAFLD. Fibrosis mainly involves the deposition of fibers around vessels. Current deep learning-based fi-brosis staging methods learn spatial relationships between tissue patches but do not explicitly consider the relation-ships between vessels and fibers, leading to limited performance and poor interpretability. In this paper, we propose an eXplicit vessel-fiber modeling method for Fibrosis staging from liver biopsy images, namely XFibrosis. Specifically, we transform vessels and fibers into graph-structured representations, where their micro-structures are depicted by vessel-induced primal graphs andfiber-induced dual graphs, respectively. Moreover, the fiber-induced dual graphs also represent the connectivity information between vessels caused by fiber deposition. A primal-dual graph convolution module is designed to facilitate the learning of spatial relationships between vessels and fibers, allowing for the joint exploration and interaction of their micro-structures. Experiments conducted on two datasets have shown that explicitly modeling the relationship between vessels and fibers leads to improved fibrosis staging and en-hanced interpretability.

Abstract While IMU based motion capture offers a cost‐effective alternative to premium camera‐based systems, it often falls short in matching the latter's realism. Common distortions, such as self‐penetrating body parts, foot skating, and floating, limit the usability of these systems, particularly for high‐end users. To address this, we employed reinforcement learning to train an AI agent that mimics erroneous sample motion. Since our agent operates within a simulated environment, it inherently avoids generating these distortions since it must adhere to the laws of physics. Impressively, the agent manages to mimic the sample motions while preserving their distinctive characteristics. We assessed our method's efficacy across various types of input data, showcasing an ideal blend of artefact‐laden IMU‐based data with high‐grade optical motion capture data. Furthermore, we compared the configuration of observation and action spaces with other implementations, pinpointing the most suitable configuration for our purposes. All our models underwent rigorous evaluation using a spectrum of quantitative metrics complemented by a qualitative review. These evaluations were performed using a benchmark dataset of IMU‐based motion data from actors not included in the training data.

Coronavirus disease 2019 (COVID-19) has become a severe global pandemic. Accurate pneumonia infection segmentation is important for assisting doctors in diagnosing COVID-19. Deep learning-based methods can be developed for automatic segmentation, but the lack of large-scale well-annotated COVID-19 training datasets may hinder their performance. Semi-supervised segmentation is a promising solution which explores large amounts of unlabelled data, while most existing methods focus on pseudo-label refinement. In this paper, we propose a new perspective on semi-supervised learning for COVID-19 pneumonia infection segmentation, namely pseudo-label guided image synthesis. The main idea is to keep the pseudo-labels and synthesize new images to match them. The synthetic image has the same COVID-19 infected regions as indicated in the pseudo-label, and the reference style extracted from the style code pool is added to make it more realistic. We introduce two representative methods by incorporating the synthetic images into model training, including single-stage Synthesis-Assisted Cross Pseudo Supervision (SA-CPS) and multi-stage Synthesis-Assisted Self-Training (SA-ST), which can work individually as well as cooperatively. Synthesis-assisted methods expand the training data with high-quality synthetic data, thus improving the segmentation performance. Extensive experiments on two COVID-19 CT datasets for segmenting the infections demonstrate our method is superior to existing schemes for semi-supervised segmentation, and achieves the state-of-the-art performance on both datasets. Code is available at: https://github.com/FeiLyu/SASSL.

High fidelity interactions between game characters and gaseous effects like smoke, fire and explosions are often neglected in realtime applications due to the high computational cost of simulating fluids. In addition, the pose of game characters is only known at runtime as it depends on input from the user. Thus simulation-suitable representations of surface geometry must be generated on the fly. Common approaches like conversion into signed distance fields are not feasible for high-resolution geometry due to the computational cost and the amount of memory required on the GPU to store these fields. We present a purely vortex particle based fluid model for games which is capable of resolving the collision between fluids and complex objects such as moving game characters in real time. To handle collisions, we use a collocation method which only require a set of disassociated particles stuck to collision surfaces. Contrary to most other vorticity based methods, we use a simple inversion free approach to obtain the collision velocity field on surfaces while at the same time avoiding the expensive pressure projection step associated with pressure based fluid solvers.

Soft robots are advantageous in terms of flexibility, safety and adaptability. It is challenging to find efficient computational approaches for planning and controlling their motion. This work takes a direct data-driven approach to learn the kinematics of the three-dimensional shape of a soft robot, by using visual markers. No prior information about the robot at hand is required. The model is oblivious to the design of the robot and type of actuation system. This allows adaptation to erroneous manufacturing. We present a highly versatile and inexpensive learning cube environment for collecting and analysing data. We prove that using multiple, lower order models of data opposed to one global, higher order model, will reduce the required data quantity, time complexity and memory complexity significantly without compromising accuracy. Further, our approach allows for embarrassingly parallelism. Yielding an overall much more simple and efficient approach.

Neural networks are becoming more and more popular for the analysis of physiological time-series. The most successful deep learning systems in this domain combine convolutional and recurrent layers to extract useful features to model temporal relations. Unfortunately, these recurrent models are difficult to tune and optimize. In our experience, they often require task-specific modifications, which makes them challenging to use for non-experts. We propose U-Time, a fully feed-forward deep learning approach to physiological time series segmentation developed for the analysis of sleep data. U-Time is a temporal fully convolutional network based on the U-Net architecture that was originally proposed for image segmentation. U-Time maps sequential inputs of arbitrary length to sequences of class labels on a freely chosen temporal scale. This is done by implicitly classifying every individual time-point of the input signal and aggregating these classifications over fixed intervals to form the final predictions. We evaluated U-Time for sleep stage classification on a large collection of sleep electroencephalography (EEG) datasets. In all cases, we found that U-Time reaches or outperforms current state-of-the-art deep learning models while being much more robust in the training process and without requiring architecture or hyperparameter adaptation across tasks.

Diffeomorphic deformation is a popular choice in medical image registration. A fundamental property of diffeomorphisms is invertibility, implying that once the relation between two points A to B is found, then the relation B to A is given per definition. Consistency is a measure of a numerical algorithm's ability to mimic this invertibility, and achieving consistency has proven to be a challenge for many state-of-the-art algorithms. We present CDD (Collocation for Diffeomorphic Deformations), a numerical solution to diffeomorphic image registration, which solves for the Stationary Velocity Field (SVF) using an implicit A-stable collocation method. CDD guarantees the preservation of the diffeomorphic properties at all discrete points and is thereby consistent to machine precision. We compared CDD's collocation method with the following standard methods: Scaling and Squaring, Forward Euler, and Runge-Kutta 4, and found that CDD is up to 9 orders of magnitude more consistent. Finally, we evaluated CDD on a number of standard bench-mark data sets and compared the results with current state-of-the-art methods: SPM-DARTEL, Diffeomorphic Demons and SyN. We found that CDD outperforms state-of-the-art methods in consistency and delivers comparable or superior registration precision.

In this paper, we propose a multi-scale, multi-kernel shape, compactly supported kernel bundle framework for stationary velocity field-based image registration (Wendland kernel bundle stationary velocity field, wKB-SVF). We exploit the possibility of directly choosing kernels to construct a reproducing kernel Hilbert space (RKHS) instead of imposing it from a differential operator. The proposed framework allows us to minimize computational cost without sacrificing the theoretical foundations of SVF-based diffeomorphic registration. In order to recover deformations occurring at different scales, we use compactly supported Wendland kernels at multiple scales and orders to parameterize the velocity fields, and the framework allows simultaneous optimization over all scales. The performance of wKB-SVF is extensively compared to the 14 non-rigid registration algorithms presented in a recent comparison paper. On both MGH10 and CUMC12 datasets, the accuracy of wKB-SVF is improved when compared to other registration algorithms. In a disease-specific application for intra-subject registration, atrophy scores estimated using the proposed registration scheme separates the diagnostic groups of Alzheimer's and normal controls better than the state-of-the-art segmentation technique. Experimental results show that wKB-SVF is a robust, flexible registration framework that allows theoretically well-founded and computationally efficient multi-scale representation of deformations and is equally well-suited for both inter- and intra-subject image registration.

This paper presents a unifying approach for calculating a wide range of popular, but seemingly very different, similarity measures. Our domain is the registration of n-dimensional images sampled on a regular grid, and our approach is well suited for gradient-based optimization algorithms. Our approach is based on local intensity histograms and built upon the technique of Locally Orderless Images. Histograms by Locally Orderless Images are well posed and offer explicit control over the three inherent and unavoidable scales: the spatial resolution, intensity levels, and spatial extent of local histograms. Through Locally Orderless Images, we offer new insight into the relations between these scales. We demonstrate our unification by developing a Locally Orderless Registration algorithm for two quite different similarity measures, namely, Normalized Mutual Information and Sum of Squared Differences, and we compare these variations both theoretically and empirically. Finally, using our algorithm, we explain the empirically observed differences between two popular joint density estimation techniques used in registration: Parzen Windows and Generalized Partial Volume.

To achieve sparse parametrizations that allow intuitive analysis, we aim to represent deformation with a basis containing interpretable elements, and we wish to use elements that have the description capacity to represent the deformation compactly. To accomplish this, we introduce in this paper higher-order momentum distributions in the large deformation diffeomorphic metric mapping (LDDMM) registration framework. While the zeroth-order moments previously used in LDDMM only describe local displacement, the first-order momenta that are proposed here represent a basis that allows local description of affine transformations and subsequent compact description of nontranslational movement in a globally nonrigid deformation. The resulting representation contains directly interpretable information from both mathematical and modeling perspectives. We develop the mathematical construction of the registration framework with higher-order momenta, we show the implications for sparse image registration and deformation description, and we provide examples of how the parametrization enables registration with a very low number of parameters. The capacity and interpretability of the parametrization using higher-order momenta lead to natural modeling of articulated movement, and the method promises to be useful for quantifying ventricle expansion and progressing atrophy during Alzheimer's disease.

Face recognition systems are typically required to work under highly varying illumination conditions. This leads to complex effects imposed on the acquired face image that pertains little to the actual identity. Consequently, illumination normalization is required to reach acceptable recognition rates in face recognition systems. In this paper, we propose an approach that integrates the face identity and illumination models under the widely used active appearance model framework as an extension to the texture model in order to obtain illumination-invariant face localization.