Expressive Forecasting of 3D Whole-body Human Motions: Predicting Future Body and Hand Movements Simultaneously
This work proposes a novel task of whole-body human motion forecasting, which jointly predicts the future activities of major body joints and hand gestures. To address this challenge, the authors introduce an Encoding-Alignment-Interaction (EAI) framework that effectively captures the heterogeneous information and cross-context interaction within the whole body.
Scene-Aware 3D Human Motion Forecasting via Mutual Distance Prediction
The core message of this paper is to propose a novel mutual distance representation that explicitly models the interaction between the human body and the 3D scene, enabling more accurate and coherent prediction of future human motion.
Comprehensive Joint Relation Modeling with Attention to Motion Coordination for Realistic Human Motion Prediction
The core message of this article is to model the global motion coordination of all joints, in addition to the local interactions between joint pairs, to generate more realistic and accurate human motion predictions.
LaCE-LHMP: Airflow Modelling-Inspired Long-Term Human Motion Prediction
Enhancing human motion prediction through laminar component extraction inspired by airflow modeling.
© 2024 by Linnk AI