Pose-ndf: Modeling human pose manifolds with neural distance fields

G Tiwari, D Antić, JE Lenssen, N Sarafianos… - … on Computer Vision, 2022 - Springer
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 …

Cams: Canonicalized manipulation spaces for category-level functional hand-object manipulation synthesis

J Zheng, Q Zheng, L Fang, Y Liu… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
In this work, we focus on a novel task of category-level functional hand-object manipulation
synthesis covering both rigid and articulated object categories. Given an object geometry, an …

Couch: Towards controllable human-chair interactions

X Zhang, BL Bhatnagar, S Starke, V Guzov… - … on Computer Vision, 2022 - Springer
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 …
[Free GPT-4]
H Zhang, S Christen, Z Fan, L Zheng… - … Conference on 3D …, 2024 - ieeexplore.ieee.org
We present ArtiGrasp, a novel method to synthesize bimanual hand-object interactions that
include gras** and articulation. This task is challenging due to the diversity of the global …

Learned vertex descent: A new direction for 3d human model fitting

E Corona, G Pons-Moll, G Alenya… - European Conference on …, 2022 - Springer
We propose a novel optimization-based paradigm for 3D human model fitting on images
and scans. In contrast to existing approaches that directly regress the parameters of a low …