Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Antic, Dimitrije"'
We focus on recovering 3D object pose and shape from single images. This is highly challenging due to strong (self-)occlusions, depth ambiguities, the enormous shape variance, and lack of 3D ground truth for natural images. Recent work relies mostly
Externí odkaz:
http://arxiv.org/abs/2409.16178
Synthesizing 3D whole-bodies that realistically grasp objects is useful for animation, mixed reality, and robotics. This is challenging, because the hands and body need to look natural w.r.t. each other, the grasped object, as well as the local scene
Externí odkaz:
http://arxiv.org/abs/2408.16770
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:
Tiwari, Garvita, Antic, Dimitrije, Lenssen, Jan Eric, Sarafianos, Nikolaos, Tung, Tony, Pons-Moll, Gerard
Publikováno v:
European Conference on Computer Vision (ECCV 2022), Oral Presentation
We present Pose-NDF, a continuous model for plausible human poses based on neural distance fields (NDFs). Pose or motion priors are important for generating realistic new poses and for reconstructing accurate poses from noisy or partial observations.
Externí odkaz:
http://arxiv.org/abs/2207.13807
Capturing aleatoric uncertainty is a critical part of many machine learning systems. In deep learning, a common approach to this end is to train a neural network to estimate the parameters of a heteroscedastic Gaussian distribution by maximizing the
Externí odkaz:
http://arxiv.org/abs/2203.09168