Zobrazeno 1 - 10
of 26
pro vyhledávání: '"Bhatnagar, Bharat Lal"'
Generating realistic hand motion sequences in interaction with objects has gained increasing attention with the growing interest in digital humans. Prior work has illustrated the effectiveness of employing occupancy-based or distance-based virtual se
Externí odkaz:
http://arxiv.org/abs/2404.01758
Autor:
Zhang, Xiaohan, Bhatnagar, Bharat Lal, Starke, Sebastian, Petrov, Ilya, Guzov, Vladimir, Dhamo, Helisa, Pérez-Pellitero, Eduardo, Pons-Moll, Gerard
Interactions between human and objects are influenced not only by the object's pose and shape, but also by physical attributes such as object mass and surface friction. They introduce important motion nuances that are essential for diversity and real
Externí odkaz:
http://arxiv.org/abs/2403.11237
Autor:
Zhang, Siwei, Bhatnagar, Bharat Lal, Xu, Yuanlu, Winkler, Alexander, Kadlecek, Petr, Tang, Siyu, Bogo, Federica
We propose RoHM, an approach for robust 3D human motion reconstruction from monocular RGB(-D) videos in the presence of noise and occlusions. Most previous approaches either train neural networks to directly regress motion in 3D or learn data-driven
Externí odkaz:
http://arxiv.org/abs/2401.08570
Autor:
Xie, Xianghui, Wang, Xi, Athanasiou, Nikos, Bhatnagar, Bharat Lal, Huang, Chun-Hao P., Mo, Kaichun, Chen, Hao, Jia, Xia, Zhang, Zerui, Cui, Liangxian, Lin, Xiao, Qian, Bingqiao, Xiao, Jie, Yang, Wenfei, Nam, Hyeongjin, Jung, Daniel Sungho, Kim, Kihoon, Lee, Kyoung Mu, Hilliges, Otmar, Pons-Moll, Gerard
Modeling the interaction between humans and objects has been an emerging research direction in recent years. Capturing human-object interaction is however a very challenging task due to heavy occlusion and complex dynamics, which requires understandi
Externí odkaz:
http://arxiv.org/abs/2401.04143
Reconstructing human-object interaction in 3D from a single RGB image is a challenging task and existing data driven methods do not generalize beyond the objects present in the carefully curated 3D interaction datasets. Capturing large-scale real dat
Externí odkaz:
http://arxiv.org/abs/2312.07063
Digital humans and, especially, 3D facial avatars have raised a lot of attention in the past years, as they are the backbone of several applications like immersive telepresence in AR or VR. Despite the progress, facial avatars reconstructed from comm
Externí odkaz:
http://arxiv.org/abs/2311.13655
Autor:
Xue, Yuxuan, Bhatnagar, Bharat Lal, Marin, Riccardo, Sarafianos, Nikolaos, Xu, Yuanlu, Pons-Moll, Gerard, Tung, Tony
Obtaining personalized 3D animatable avatars from a monocular camera has several real world applications in gaming, virtual try-on, animation, and VR/XR, etc. However, it is very challenging to model dynamic and fine-grained clothing deformations fro
Externí odkaz:
http://arxiv.org/abs/2308.14847
Capturing the interactions between humans and their environment in 3D is important for many applications in robotics, graphics, and vision. Recent works to reconstruct the 3D human and object from a single RGB image do not have consistent relative tr
Externí odkaz:
http://arxiv.org/abs/2303.16479
We present TOCH, a method for refining incorrect 3D hand-object interaction sequences using a data prior. Existing hand trackers, especially those that rely on very few cameras, often produce visually unrealistic results with hand-object intersection
Externí odkaz:
http://arxiv.org/abs/2205.07982
Humans interact with an object in many different ways by making contact at different locations, creating a highly complex motion space that can be difficult to learn, particularly when synthesizing such human interactions in a controllable manner. Ex
Externí odkaz:
http://arxiv.org/abs/2205.00541