Related papers: Motion In-Betweening with Phase Manifolds

We present a unified perspective on tackling various human-centric video tasks by learning human motion representations from large-scale and heterogeneous data resources. Specifically, we propose a pretraining stage in which a motion…

We present a novel method for populating 3D indoor scenes with virtual humans that can navigate in the environment and interact with objects in a realistic manner. Existing approaches rely on training sequences that contain captured human…

We identify a new "order parameter" for the disorder driven many-body localization (MBL) transition by leveraging artificial intelligence. This allows us to pin down the transition, as the point at which the physics changes qualitatively,…

We present a method that finds locomanipulation plans that perform simultaneous locomotion and manipulation of objects for a desired end-effector trajectory. Key to our approach is to consider a generic locomotion constraint manifold that…

Short-term human pose prediction plays a crucial role in interactive systems, assistive robots, and emotion-aware human-computer interaction[1-3]. While current trajectory prediction models primarily rely on geometric motion cues, they…

Incorporating temporal information effectively is important for accurate 3D human motion estimation and generation which have wide applications from human-computer interaction to AR/VR. In this paper, we present MoManifold, a novel human…

We employ unsupervised machine learning techniques to learn latent parameters which best describe states of the two-dimensional Ising model and the three-dimensional XY model. These methods range from principal component analysis to…

This paper proposes a method for performing continual learning of predictive models that facilitate the inference of future frames in video sequences. For a first given experience, an initial Variational Autoencoder, together with a set of…

Predicting high-fidelity future human poses, from a historically observed sequence, is decisive for intelligent robots to interact with humans. Deep end-to-end learning approaches, which typically train a generic pre-trained model on…

Motion style transfer is highly desired for motion generation systems for gaming. Compared to its offline counterpart, the research on online motion style transfer under interactive control is limited. In this work, we propose an end-to-end…

Learning shared structure across environments facilitates rapid learning and adaptive behavior in neural systems. This has been widely demonstrated and applied in machine learning to train models that are capable of generalizing to novel…

Dynamical systems (DS) methods for Learning-from-Demonstration (LfD) provide stable, continuous policies from few demonstrations. First-order dynamical systems (DS) are effective for many point-to-point and periodic tasks, as long as a…

Generalizing motion representation across diverse characters remains challenging due to significant topological variations in skeletal structures across datasets and species, which hinder the development of scalable generative models. To…

Conventional methods for human motion synthesis are either deterministic or struggle with the trade-off between motion diversity and motion quality. In response to these limitations, we introduce MoFusion, i.e., a new…

Generating videos of complex human motions such as flips, cartwheels, and martial arts remains challenging for current video diffusion models. Text-only conditioning is temporally ambiguous for fine-grained motion control, while explicit…

Controllable character image animation has a wide range of applications. Although existing studies have consistently improved performance, challenges persist in the field of character image animation, particularly concerning stability in…

If a given behavior of a multi-agent system restricts the phase variable to a invariant manifold, then we define a phase transition as change of physical characteristics such as speed, coordination, and structure. We define such a phase…

This work proposes an autoencoder neural network as a non-linear generalization of projection-based methods for solving Partial Differential Equations (PDEs). The proposed deep learning architecture presented is capable of generating the…

3D human motion prediction is a research area of high significance and a challenge in computer vision. It is useful for the design of many applications including robotics and autonomous driving. Traditionally, autogregressive models have…

Large and diverse datasets have been the cornerstones of many impressive advancements in artificial intelligence. Intelligent creatures, however, learn by interacting with the environment, which changes the input sensory signals and the…