Related papers: Exploring Versatile Prior for Human Motion via Mot…
The modeling of human motion using machine learning methods has been widely studied. In essence it is a time-series modeling problem involving predicting how a person will move in the future given how they moved in the past. Existing…
Recent advances in learning reusable motion priors have demonstrated their effectiveness in generating naturalistic behaviors. In this paper, we propose a new learning framework in this paradigm for controlling physics-based characters with…
We introduce a principled, data-driven approach for modeling a neural prior over human body poses using normalizing flows. Unlike heuristic or low-expressivity alternatives, our method leverages RealNVP to learn a flexible density over…
Recent progress in stochastic motion prediction, i.e., predicting multiple possible future human motions given a single past pose sequence, has led to producing truly diverse future motions and even providing control over the motion of some…
Human motion prediction is a stochastic process: Given an observed sequence of poses, multiple future motions are plausible. Existing approaches to modeling this stochasticity typically combine a random noise vector with information about…
Motion capture from a monocular video is fundamental and crucial for us humans to naturally experience and interact with each other in Virtual Reality (VR) and Augmented Reality (AR). However, existing methods still struggle with…
Removing pixel-wise heterogeneous motion blur is challenging due to the ill-posed nature of the problem. The predominant solution is to estimate the blur kernel by adding a prior, but the extensive literature on the subject indicates the…
Understanding and anticipating human activity is an important capability for intelligent systems in mobile robotics, autonomous driving, and video surveillance. While learning from demonstrations with on-site collected trajectory data is a…
We present an approach to modeling an image-space prior on scene motion. Our prior is learned from a collection of motion trajectories extracted from real video sequences depicting natural, oscillatory dynamics such as trees, flowers,…
Most computational accounts of cognitive maps assume that stability is achieved primarily through sensory anchoring, with self-motion contributing to incremental positional updates only. However, biological spatial representations often…
Data uncertainty in practical person reID is ubiquitous, hence it requires not only learning the discriminative features, but also modeling the uncertainty based on the input. This paper proposes to learn the sample posterior and the class…
Recent work has demonstrated the significant potential of denoising diffusion models for generating human motion, including text-to-motion capabilities. However, these methods are restricted by the paucity of annotated motion data, a focus…
Generating accurate and efficient predictions for the motion of the humans present in the scene is key to the development of effective motion planning algorithms for robots moving in promiscuous areas, where wrong planning decisions could…
Predicting diverse object motions from a single static image remains challenging, as current video generation models often entangle object movement with camera motion and other scene changes. While recent methods can predict specific…
Smooth and seamless robot navigation while interacting with humans depends on predicting human movements. Forecasting such human dynamics often involves modeling human trajectories (global motion) or detailed body joint movements (local…
The task of action-driven human motion prediction aims to forecast future human motion based on the observed sequence while respecting the given action label. It requires modeling not only the stochasticity within human motion but the…
This paper proposes a novel generative video compression framework that leverages motion pattern priors, derived from subtle dynamics in common scenes (e.g., swaying flowers or a boat drifting on water), rather than relying on video content…
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…
Natural and lifelike locomotion remains a fundamental challenge for humanoid robots to interact with human society. However, previous methods either neglect motion naturalness or rely on unstable and ambiguous style rewards. In this paper,…
This paper tackles video prediction from a new dimension of predicting spacetime-varying motions that are incessantly changing across both space and time. Prior methods mainly capture the temporal state transitions but overlook the complex…