Zobrazeno 1 - 10
of 142
pro vyhledávání: '"Pons-Moll, Gerard"'
Autor:
Sárándi, István, Pons-Moll, Gerard
With the explosive growth of available training data, single-image 3D human modeling is ahead of a transition to a data-centric paradigm. A key to successfully exploiting data scale is to design flexible models that can be supervised from various het
Externí odkaz:
http://arxiv.org/abs/2407.07532
Creating realistic avatars from a single RGB image is an attractive yet challenging problem. Due to its ill-posed nature, recent works leverage powerful prior from 2D diffusion models pretrained on large datasets. Although 2D diffusion models demonst
Externí odkaz:
http://arxiv.org/abs/2406.08475
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:
Yunus, Raza, Lenssen, Jan Eric, Niemeyer, Michael, Liao, Yiyi, Rupprecht, Christian, Theobalt, Christian, Pons-Moll, Gerard, Huang, Jia-Bin, Golyanik, Vladislav, Ilg, Eddy
Reconstructing models of the real world, including 3D geometry, appearance, and motion of real scenes, is essential for computer graphics and computer vision. It enables the synthesizing of photorealistic novel views, useful for the movie industry an
Externí odkaz:
http://arxiv.org/abs/2403.15064
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
Faithfully modeling the space of articulations is a crucial task that allows recovery and generation of realistic poses, and remains a notorious challenge. To this end, we introduce Neural Riemannian Distance Fields (NRDFs), data-driven priors modeli
Externí odkaz:
http://arxiv.org/abs/2403.03122
3D Clothing modeling and datasets play crucial role in the entertainment, animation, and digital fashion industries. Existing work often lacks detailed semantic understanding or uses synthetic datasets, lacking realism and personalization. To address
Externí odkaz:
http://arxiv.org/abs/2401.12051
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
Aligning a template to 3D human point clouds is a long-standing problem crucial for tasks like animation, reconstruction, and enabling supervised learning pipelines. Recent data-driven methods leverage predicted surface correspondences. However, they
Externí odkaz:
http://arxiv.org/abs/2312.14024
We present Paint-it, a text-driven high-fidelity texture map synthesis method for 3D meshes via neural re-parameterized texture optimization. Paint-it synthesizes texture maps from a text description by synthesis-through-optimization, exploiting the
Externí odkaz:
http://arxiv.org/abs/2312.11360