Recent advances in shape correspondence

Y Sahillioğlu - The Visual Computer, 2020 - Springer
Important new developments have appeared since the most recent direct survey on shape
correspondence published almost a decade ago. Our survey covers the period from 2011 …

A survey on deep geometry learning: From a representation perspective

YP Xiao, YK Lai, FL Zhang, C Li, L Gao - Computational Visual Media, 2020 - Springer
Researchers have achieved great success in dealing with 2D images using deep learning.
In recent years, 3D computer vision and geometry deep learning have gained ever more …

Implicit geometric regularization for learning shapes

A Gropp, L Yariv, N Haim, M Atzmon… - arXiv preprint arXiv …, 2020 - arxiv.org
Representing shapes as level sets of neural networks has been recently proved to be useful
for different shape analysis and reconstruction tasks. So far, such representations were …

Sal: Sign agnostic learning of shapes from raw data

M Atzmon, Y Lipman - … of the IEEE/CVF conference on …, 2020 - openaccess.thecvf.com
Recently, neural networks have been used as implicit representations for surface
reconstruction, modelling, learning, and generation. So far, training neural networks to be …

Dynamic graph cnn for learning on point clouds

Y Wang, Y Sun, Z Liu, SE Sarma… - ACM Transactions on …, 2019 - dl.acm.org
Point clouds provide a flexible geometric representation suitable for countless applications
in computer graphics; they also comprise the raw output of most 3D data acquisition devices …

Pointcnn: Convolution on x-transformed points

Y Li, R Bu, M Sun, W Wu, X Di… - Advances in neural …, 2018 - proceedings.neurips.cc
We present a simple and general framework for feature learning from point cloud. The key to
the success of CNNs is the convolution operator that is capable of leveraging spatially-local …

A papier-mâché approach to learning 3d surface generation

T Groueix, M Fisher, VG Kim… - Proceedings of the …, 2018 - openaccess.thecvf.com
We introduce a method for learning to generate the surface of 3D shapes. Our approach
represents a 3D shape as a collection of parametric surface elements and, in contrast to …

Meshcnn: a network with an edge

R Hanocka, A Hertz, N Fish, R Giryes… - ACM Transactions on …, 2019 - dl.acm.org
Polygonal meshes provide an efficient representation for 3D shapes. They explicitly
captureboth shape surface and topology, and leverage non-uniformity to represent large flat …

Generating 3D faces using convolutional mesh autoencoders

A Ranjan, T Bolkart, S Sanyal… - Proceedings of the …, 2018 - openaccess.thecvf.com
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 …

Diffusionnet: Discretization agnostic learning on surfaces

N Sharp, S Attaiki, K Crane, M Ovsjanikov - ACM Transactions on …, 2022 - dl.acm.org
We introduce a new general-purpose approach to deep learning on three-dimensional
surfaces based on the insight that a simple diffusion layer is highly effective for spatial …