Dual octree graph networks for learning adaptive volumetric shape representations

• Published in: ACM transactions on graphics Vol. 41; no. 4; pp. 1 - 15
• Main Authors: Wang, Peng-Shuai, Liu, Yang, Tong, Xin
• Format: Journal Article
• Language: English
• Published: New York, NY, USA ACM 22.07.2022
• Subjects: Computer graphics; Computing methodologies; Machine learning; Machine learning approaches; Mesh models; Neural networks; Shape modeling; dual octree; graph neural networks; surface reconstruction; volumetric representations

We present an adaptive deep representation of volumetric fields of 3D shapes and an efficient approach to learn this deep representation for high-quality 3D shape reconstruction and auto-encoding. Our method encodes the volumetric field of a 3D shape with an adaptive feature volume organized by an o...