Related papers: A Skeleton-Driven Neural Occupancy Representation …

The standard engineering approach when facing uncertainty is modelling. Mixing data from a well-calibrated model with real recordings has led to breakthroughs in many applications of AI, from computer vision to autonomous driving. This type…

We present a dataset for force-grounded, cross-view articulated manipulation that couples what is seen with what is done and what is felt during real human interaction. The dataset contains 3048 sequences across 381 articulated objects in…

We introduce and evaluate several architectures for Convolutional Neural Networks to predict the 3D joint locations of a hand given a depth map. We first show that a prior on the 3D pose can be easily introduced and significantly improves…

Language-specified mobile manipulation tasks in novel environments simultaneously face challenges interacting with a scene which is only partially observed, grounding semantic information from language instructions to the partially observed…

Manipulating articulated tools, such as tweezers or scissors, has rarely been explored in previous research. Unlike rigid tools, articulated tools change their shape dynamically, creating unique challenges for dexterous robotic hands. In…

Previous methods for skeleton-based gesture recognition mostly arrange the skeleton sequence into a pseudo picture or spatial-temporal graph and apply deep Convolutional Neural Network (CNN) or Graph Convolutional Network (GCN) for feature…

Discriminative methods often generate hand poses kinematically implausible, then generative methods are used to correct (or verify) these results in a hybrid method. Estimating 3D hand pose in a hierarchy, where the high-dimensional output…

Recent progress in 3D hand--object interaction (HOI) generation has primarily focused on single--hand grasp synthesis, while bimanual manipulation remains significantly more challenging. Long--horizon planning instability, fine--grained…

Spatiotemporal representations learned using 3D convolutional neural networks (CNN) are currently used in state-of-the-art approaches for action related tasks. However, 3D-CNN are notorious for being memory and compute resource intensive as…

Millions of people around the world face motor impairments due to Parkinson's, cerebral palsy, muscular dystrophy and other physical disabilities. The goal of this project is to increase the usable surface-area of devices for users with…

Since humans interact with diverse objects every day, the holistic 3D capture of these interactions is important to understand and model human behaviour. However, most existing methods for hand-object reconstruction from RGB either assume…

This paper targets unsupervised skeleton-based action representation learning and proposes a new Hierarchical Contrast (HiCo) framework. Different from the existing contrastive-based solutions that typically represent an input skeleton…

We present HandAvatar, a novel representation for hand animation and rendering, which can generate smoothly compositional geometry and self-occlusion-aware texture. Specifically, we first develop a MANO-HD model as a high-resolution mesh…

Articulated 3D reconstruction has valuable applications in various domains, yet it remains costly and demands intensive work from domain experts. Recent advancements in template-free learning methods show promising results with monocular…

We present the HANDAL dataset for category-level object pose estimation and affordance prediction. Unlike previous datasets, ours is focused on robotics-ready manipulable objects that are of the proper size and shape for functional grasping…

Scalable learning of dexterous manipulation remains bottlenecked by the difficulty of collecting natural, high-fidelity human demonstrations of multi-finger hands due to occlusion, complex hand kinematics, and contact-rich interactions. We…

Modeling human decision-making is central to applications such as recommendation, preference learning, and human-AI alignment. While many classic models assume context-independent choice behavior, a large body of behavioral research shows…

Recognizing human actions in untrimmed videos is an important challenging task. An effective 3D motion representation and a powerful learning model are two key factors influencing recognition performance. In this paper we introduce a new…

We present an approach that can reconstruct hands in 3D from monocular input. Our approach for Hand Mesh Recovery, HaMeR, follows a fully transformer-based architecture and can analyze hands with significantly increased accuracy and…

The hand, a complex effector comprising dozens of degrees of freedom of movement, endows us with the ability to flexibly, precisely, and effortlessly interact with objects. The neural signals associated with dexterous hand movements in…