As it is hard to calibrate single-view RGB images in the wild, existing 3D human mesh
reconstruction (3DHMR) methods either use a constant large focal length or estimate one …

Learning 3D human-object interaction relation is pivotal to embodied AI and interaction
modeling. Most existing methods approach the goal by learning to predict isolated …

Normal estimation for 3D point clouds is a fundamental task in 3D geometry processing. The
state-of-the-art methods rely on priors of fitting local surfaces learned from normal …

In this paper, we propose a new method, called DoubleCoverUDF, for extracting the zero
level-set from unsigned distance fields (UDFs). DoubleCoverUDF takes a learned UDF and …

The rise of artificial intelligence generated content (AIGC) has been remarkable in the
language and image fields, but artificial intelligence (AI) generated three-dimensional (3D) …

The rapid development of AR/VR brings tremendous demands for 3D content. While the
widely-used Computer-Aided Design (CAD) method requires a time-consuming and labor …

We propose Neural Gradient Learning (NGL), a deep learning approach to learn gradient
vectors with consistent orientation from 3D point clouds for normal estimation. It has …

The past few years have witnessed the great success and prevalence of self-supervised
representation learning within the language and 2D vision communities. However, such …

In the realm of digital creativity, our potential to craft intricate 3D worlds from imagination is
often hampered by the limitations of existing digital tools, which demand extensive expertise …

We propose a novel method called SHS-Net for point cloud normal estimation by learning
signed hyper surfaces, which can accurately predict normals with global consistent …