Pose-ndf: Modeling human pose manifolds with neural distance fields
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 …
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
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 …
synthesis covering both rigid and articulated object categories. Given an object geometry, an …
Couch: Towards controllable human-chair interactions
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 …
locations, creating a highly complex motion space that can be difficult to learn, particularly …
[Free GPT-4]
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 …
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
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 …
and scans. In contrast to existing approaches that directly regress the parameters of a low …