Paper Info
Title
CvxNet: Learnable Convex Decomposition
Abstract
Any solid object can be decomposed into a collection of convex polytopes (in short, convexes). When a small number of convexes are used, such a decomposition can be thought of as a piece-wise approximation of the geometry. This decomposition is fundamental in computer graphics, where it provides one of the most common ways to approximate geometry, for example, in real-time physics simulation. A convex object also has the property of being simultaneously an explicit and implicit representation: one can interpret it explicitly as a mesh derived by computing the vertices of a convex hull, or implicitly as the collection of half-space constraints or support functions. Their implicit representation makes them particularly well suited for neural network training, as they abstract away from the topology of the geometry they need to represent. However, at testing time, convexes can also generate explicit representations - polygonal meshes - which can then be used in any downstream application. We introduce a network architecture to represent a low dimensional family of convexes. This family is automatically derived via an auto-encoding process. We investigate the applications of this architecture including automatic convex decomposition, image to 3D reconstruction, and part-based shape retrieval.
Year
DOI
Venue
2020
10.1109/CVPR42600.2020.00011
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Keywords
DocType
ISSN
piece-wise approximation,explicit representation,implicit representation,convex decomposition,solid object,convex polytopes,computer graphics,neural network training
Conference
1063-6919
ISBN
Citations 
PageRank 
978-1-7281-7169-2
7
0.42
References 
Authors
49
6
Name
Order
Citations
PageRank
Boyang Deng1272.84
Kyle Genova2293.83
Soroosh Yazdani3152.46
Sofien Bouaziz493435.79
geoffrey e hinton5404354751.69
Andrea Tagliasacchi671631.90