相关论文: MotionAug: Augmentation with Physical Correction f…

Styled motion in-betweening is crucial for computer animation and gaming. However, existing methods typically encode motion styles by modeling whole-body motions, often overlooking the representation of individual body parts. This…

Enhancing the generalization capability of robotic learning to enable robots to operate effectively in diverse, unseen scenes is a fundamental and challenging problem. Existing approaches often depend on pretraining with large-scale data…

Inertial measurement units (IMUs) increasingly function as a basic component of wearable sensor network (WSN)systems. IMU-based joint angle estimation (JAE) is a relatively typical usage of IMUs, with extensive applications. However, the…

This paper introduces a novel human pose estimation approach using sparse inertial sensors, addressing the shortcomings of previous methods reliant on synthetic data. It leverages a diverse array of real inertial motion capture data from…

Physics-based character animation has become a fundamental approach for synthesizing realistic, physically plausible motions. While current data-driven deep reinforcement learning (DRL) methods can synthesize complex skills, they struggle…

Because imitation learning relies on human demonstrations in hard-to-simulate settings, the inclusion of force control in this method has resulted in a shortage of training data, even with a simple change in speed. Although the field of…

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…

Generalising vision-based manipulation policies to novel environments remains a challenging area with limited exploration. Current practices involve collecting data in one location, training imitation learning or reinforcement learning…

Image animation is the task of transferring the motion of a driving video to a given object in a source image. While great progress has recently been made in unsupervised motion transfer, requiring no labeled data or domain priors, many…

This paper addresses the problem of generating whole-body motion from speech. Despite great successes, prior methods still struggle to produce reasonable and diverse whole-body motions from speech. This is due to their reliance on…

This paper tackles the problem of physics-aware human motion synthesis in a dynamic scene. Unlike existing works which mainly tend to generate physically unrealistic motions due to limited contact modeling, typically restricted to hands, in…

Deep learning approaches deliver state-of-the-art performance in recognition of spatiotemporal human motion data. However, one of the main challenges in these recognition tasks is limited available training data. Insufficient training data…

Action recognition is a relatively established task, where givenan input sequence of human motion, the goal is to predict its ac-tion category. This paper, on the other hand, considers a relativelynew problem, which could be thought of as…

Real-time computational speed and a high degree of precision are requirements for computer-assisted interventions. Applying a segmentation network to a medical video processing task can introduce significant inter-frame prediction noise.…

Data augmentation is a dominant method for reducing model overfitting and improving generalization. Most existing data augmentation methods tend to find a compromise in augmenting the data, \textit{i.e.}, increasing the amplitude of…

3D Human motion generation is pivotal across film, animation, gaming, and embodied intelligence. Traditional 3D motion synthesis relies on costly motion capture, while recent work shows that 2D videos provide rich, temporally coherent…

Due to the lack of diversity of datasets, the generalization ability of the pose estimator is poor. To solve this problem, we propose a pose augmentation solution via DH forward kinematics model, which we call DH-AUG. We observe that the…

Incorporating physics in human motion capture to avoid artifacts like floating, foot sliding, and ground penetration is a promising direction. Existing solutions always adopt kinematic results as reference motions, and the physics is…

Text-guided motion editing enables high-level semantic control and iterative modifications beyond traditional keyframe animation. Existing methods rely on limited pre-collected training triplets, which severely hinders their versatility in…

Stochastic human motion prediction aims to forecast multiple plausible future motions given a single pose sequence from the past. Most previous works focus on designing elaborate losses to improve the accuracy, while the diversity is…