Related papers: M-STAR: Multi-Scale Spatiotemporal Autoregression …
Human motion prediction is essential for the safe and smooth operation of mobile service robots and intelligent vehicles around people. Commonly used neural network-based approaches often require large amounts of complete trajectories to…
Human motion generation is a significant pursuit in generative computer vision with widespread applications in film-making, video games, AR/VR, and human-robot interaction. Current methods mainly utilize either diffusion-based generative…
We study one particular type of multivariate spatial autoregression (MSAR) model with diverging dimensions in both responses and covariates. This makes the usual MSAR models no longer applicable due to the high computational cost. To…
An effective understanding of the environment and accurate trajectory prediction of surrounding dynamic obstacles are indispensable for intelligent mobile systems (e.g. autonomous vehicles and social robots) to achieve safe and high-quality…
Trajectory generation is a pivotal task in autonomous driving. Recent studies have introduced the autoregressive paradigm, leveraging the state transition model to approximate future trajectory distributions. This paradigm closely mirrors…
This report reviews recent advancements in human motion prediction, reconstruction, and generation. Human motion prediction focuses on forecasting future poses and movements from historical data, addressing challenges like nonlinear…
Real-time character control is an essential component for interactive experiences, with a broad range of applications, including physics simulations, video games, and virtual reality. The success of diffusion models for image synthesis has…
Recently, interactive digital human video generation has attracted widespread attention and achieved remarkable progress. However, building such a practical system that can interact with diverse input signals in real time remains…
In this paper, we present a novel trajectory prediction model for autonomous driving, combining a Characterized Diffusion Module and a Spatial-Temporal Interaction Network to address the challenges posed by dynamic and heterogeneous traffic…
Motion retargeting seeks to faithfully replicate the spatio-temporal motion characteristics of a source character onto a target character with a different body shape. Apart from motion semantics preservation, ensuring geometric plausibility…
Developing robotic technologies for use in human society requires ensuring the safety of robots' navigation behaviors while adhering to pedestrians' expectations and social norms. However, maintaining real-time communication between robots…
The multi-modality and stochastic characteristics of human behavior make motion prediction a highly challenging task, which is critical for autonomous driving. While deep learning approaches have demonstrated their great potential in this…
This paper presents STARCaster, an identity-aware spatio-temporal video diffusion model that addresses both speech-driven portrait animation and free-viewpoint talking portrait synthesis, given an identity embedding or reference image,…
Series of univariate distributions indexed by equally spaced time points are ubiquitous in applications and their analysis constitutes one of the challenges of the emerging field of distributional data analysis. To quantify such…
Motion Planning, as a fundamental technology of automatic navigation for the autonomous vehicle, is still an open challenging issue in the real-life traffic situation and is mostly applied by the model-based approaches. However, due to the…
Real-time motion-controllable video generation remains challenging due to the inherent latency of bidirectional diffusion models and the lack of effective autoregressive (AR) approaches. Existing AR video diffusion models are limited to…
The unavailability of training data is a permanent source of much frustration in research, especially when it is due to privacy concerns. This is particularly true for location data since previous techniques all suffer from the inherent…
Diverse and realistic traffic scenarios are crucial for evaluating the AI safety of autonomous driving systems in simulation. This work introduces a data-driven method called TrafficGen for traffic scenario generation. It learns from the…
Understanding individual-level human mobility is critical for a wide range of applications. As such, real-world trajectory datasets provide valuable insights into actual movement behaviors and patterns of life but are often constrained by…
Recent years have witnessed an explosion of extensive geolocated datasets related to human movement, enabling scientists to quantitatively study individual and collective mobility patterns, and to generate models that can capture and…