Related papers: PALM: A Dataset and Baseline for Learning Multi-su…

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 construct the first markerless deformable interaction dataset recording interactive motions of the hands and deformable objects, called HMDO (Hand Manipulation with Deformable Objects). With our built multi-view capture system, it…

Metaverse is an immersive shared space that remote users can access through virtual and augmented reality interfaces, enabling their avatars to interact with each other and the surrounding. Although digital objects can be manipulated,…

Recently, ocular biometrics in unconstrained environments using images obtained at visible wavelength have gained the researchers' attention, especially with images captured by mobile devices. Periocular recognition has been demonstrated to…

Interactive object understanding, or what we can do to objects and how is a long-standing goal of computer vision. In this paper, we tackle this problem through observation of human hands in in-the-wild egocentric videos. We demonstrate…

Generating realistic human motion with high-level controls is a crucial task for social understanding, robotics, and animation. With high-quality MOCAP data becoming more available recently, a wide range of data-driven approaches have been…

Hand Gesture is a popular way to interact or control machines and it has been implemented in many applications. The geometry of hand is such that it is hard to construct in virtual environment and control the joints but the functionality…

For years, researchers have been devoted to generalizable object perception and manipulation, where cross-category generalizability is highly desired yet underexplored. In this work, we propose to learn such cross-category skills via…

To make 3D human avatars widely available, we must be able to generate a variety of 3D virtual humans with varied identities and shapes in arbitrary poses. This task is challenging due to the diversity of clothed body shapes, their complex…

Human video generation task has gained significant attention with the advancement of deep generative models. Generating realistic videos with human movements is challenging in nature, due to the intricacies of human body topology and…

This work studies the problem of shape reconstruction and object localization using a vision-based tactile sensor, GelSlim. The main contributions are the recovery of local shapes from contact, an approach to reconstruct the tactile shape…

We present HUP-3D, a 3D multi-view multi-modal synthetic dataset for hand-ultrasound (US) probe pose estimation in the context of obstetric ultrasound. Egocentric markerless 3D joint pose estimation has potential applications in mixed…

We interact with the world with our hands and see it through our own (egocentric) perspective. A holistic 3Dunderstanding of such interactions from egocentric views is important for tasks in robotics, AR/VR, action recognition and motion…

Mainstream large vision-language models (LVLMs) inherently encode cultural biases, highlighting the need for diverse multimodal datasets. To address this gap, we introduce PEARL, a large-scale Arabic multimodal dataset and benchmark…

Humans take advantage of real world symmetries for various tasks, yet capturing their superb symmetry perception mechanism with a computational model remains elusive. Motivated by a new study demonstrating the extremely high inter-person…

Current pre-training methods in computer vision focus on natural images in the daily-life context. However, abstract diagrams such as icons and symbols are common and important in the real world. This work is inspired by Tangram, a game…

Estimating 3D hand and object pose from a single image is an extremely challenging problem: hands and objects are often self-occluded during interactions, and the 3D annotations are scarce as even humans cannot directly label the…

We introduce InteractVLM, a novel method to estimate 3D contact points on human bodies and objects from single in-the-wild images, enabling accurate human-object joint reconstruction in 3D. This is challenging due to occlusions, depth…

Hand avatars play a pivotal role in a wide array of digital interfaces, enhancing user immersion and facilitating natural interaction within virtual environments. While previous studies have focused on photo-realistic hand rendering, little…

The availability of a large labeled dataset is a key requirement for applying deep learning methods to solve various computer vision tasks. In the context of understanding human activities, existing public datasets, while large in size, are…