Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Sanyal, Soubhik"'
Autor:
Niewiadomski, Tomasz, Yiannakidis, Anastasios, Cuevas-Velasquez, Hanz, Sanyal, Soubhik, Black, Michael J., Zuffi, Silvia, Kulits, Peter
The model-based estimation of 3D animal pose and shape from images enables computational modeling of animal behavior. Training models for this purpose requires large amounts of labeled image data with precise pose and shape annotations. However, capt
Externí odkaz:
http://arxiv.org/abs/2412.08101
We present a novel unconditional video generative model designed to address long-term spatial and temporal dependencies, with attention to computational and dataset efficiency. To capture long spatio-temporal dependencies, our approach incorporates a
Externí odkaz:
http://arxiv.org/abs/2401.06035
Autor:
Sanyal, Soubhik, Ghosh, Partha, Yang, Jinlong, Black, Michael J., Thies, Justus, Bolkart, Timo
We present SCULPT, a novel 3D generative model for clothed and textured 3D meshes of humans. Specifically, we devise a deep neural network that learns to represent the geometry and appearance distribution of clothed human bodies. Training such a mode
Externí odkaz:
http://arxiv.org/abs/2308.10638
Autor:
Sanyal, Soubhik, Vorobiov, Alex, Bolkart, Timo, Loper, Matthew, Mohler, Betty, Davis, Larry, Romero, Javier, Black, Michael J.
Synthesizing images of a person in novel poses from a single image is a highly ambiguous task. Most existing approaches require paired training images; i.e. images of the same person with the same clothing in different poses. However, obtaining suffi
Externí odkaz:
http://arxiv.org/abs/2110.05458
The estimation of 3D face shape from a single image must be robust to variations in lighting, head pose, expression, facial hair, makeup, and occlusions. Robustness requires a large training set of in-the-wild images, which by construction, lack grou
Externí odkaz:
http://arxiv.org/abs/1905.06817
Publikováno v:
European Conference on Computer Vision 2018
Learned 3D representations of human faces are useful for computer vision problems such as 3D face tracking and reconstruction from images, as well as graphics applications such as character generation and animation. Traditional models learn a latent
Externí odkaz:
http://arxiv.org/abs/1807.10267
Publikováno v:
In Pattern Recognition July 2017 67:353-365
Publikováno v:
2015 IEEE International Conference on Computer Vision (ICCV); 1/1/2015, p3837-3845, 9p