相关论文: PhysPT: Physics-aware Pretrained Transformer for E…

Transformer architectures have become the model of choice in natural language processing and are now being introduced into computer vision tasks such as image classification, object detection, and semantic segmentation. However, in the…

Advances in wearable robotics challenge the traditional definition of human motor systems, as wearable robots redefine body structure, movement capability, and perception of their own bodies. We measured gait performance and perceived body…

This paper proposes a data-driven method for powered prosthesis control that achieves stable walking without the need for additional sensors on the human. The key idea is to extract the nominal gait and the human interaction information…

Recent video diffusion models have achieved impressive capabilities as large-scale generative world models. However, these models often struggle with fine-grained physical consistency, exhibiting physically implausible dynamics over time.…

We propose a novel framework for accurate 3D human pose estimation in combat sports using sparse multi-camera setups. Our method integrates robust multi-view 2D pose tracking via a transformer-based top-down approach, employing epipolar…

Despite recent progress in video generation, producing videos that adhere to physical laws remains a significant challenge. Traditional diffusion-based methods struggle to extrapolate to unseen physical conditions (eg, velocity) due to…

Humans naturally grasp objects with minimal level required force for stability, whereas robots often rely on rigid, over-squeezing control. To narrow this gap, we propose a human-inspired physics-conditioned tactile method (Phy-Tac) for…

Human motion retargeting aims to transfer the motion of one person in a "driving" video or set of images to another person. Existing efforts leverage a long training video from each target person to train a subject-specific motion transfer…

Recognizing and localizing objects in the 3D space is a crucial ability for an AI agent to perceive its surrounding environment. While significant progress has been achieved with expensive LiDAR point clouds, it poses a great challenge for…

A video autoencoder is proposed for learning disentan- gled representations of 3D structure and camera pose from videos in a self-supervised manner. Relying on temporal continuity in videos, our work assumes that the 3D scene structure in…

Traditional 3D morphable face models (3DMMs) provide fine-grained control over expression but cannot easily capture geometric and appearance details. Neural volumetric representations approach photorealism but are hard to animate and do not…

This paper proposes a unified framework dubbed Multi-view and Temporal Fusing Transformer (MTF-Transformer) to adaptively handle varying view numbers and video length without camera calibration in 3D Human Pose Estimation (HPE). It consists…

We present a system that allows users to visualize complex human motion via 3D motion sculptures---a representation that conveys the 3D structure swept by a human body as it moves through space. Given an input video, our system computes the…

The ability to extrapolate dynamic 3D scenes beyond the observed timeframe is fundamental to advancing physical world understanding and predictive modeling. Existing dynamic 3D reconstruction methods have achieved high-fidelity rendering of…

The appearance of a human in clothing is driven not only by the pose but also by its temporal context, i.e., motion. However, such context has been largely neglected by existing monocular human modeling methods whose neural networks often…

This paper addresses the problem of cross-dataset generalization of 3D human pose estimation models. Testing a pre-trained 3D pose estimator on a new dataset results in a major performance drop. Previous methods have mainly addressed this…

This paper introduces a novel approach to monocular 3D human pose estimation using contextualized representation learning with the Transformer-GCN dual-stream model. Monocular 3D human pose estimation is challenged by depth ambiguity,…

Estimating 3D human poses from a monocular video is still a challenging task. Many existing methods' performance drops when the target person is occluded by other objects, or the motion is too fast/slow relative to the scale and speed of…

Holistic 3D human-scene reconstruction is a crucial and emerging research area in robot perception. A key challenge in holistic 3D human-scene reconstruction is to generate a physically plausible 3D scene from a single monocular RGB image.…

Shape-from-Template (SfT) methods estimate 3D surface deformations from a single monocular RGB camera while assuming a 3D state known in advance (a template). This is an important yet challenging problem due to the under-constrained nature…