IMC-NET: Learning Implicit Field with Corner Attention Network for 3D Shape Reconstruction
Jiongchao Jin, Huanqiang Xu, Pengliang Ji, Biao Leng
Abstract
Learning implicit field as shape representation brings a revolution in 3D shape single view reconstruction, while it suffers from over-smoothness of corners and details. Many involve 2D supervision to solve corners and details. However, they are limited by the number of views and the accuracy of the renderer. Thus, we propose IMC-NET, an IMplicit field with Corner attention NETwork, to reconstruct details and corners of 3D shapes without any 2D supervision. In IMC-NET, we designed a corner attention branch to predict detailed corners of 3D shape under hand-crafted 3D corner points supervision. Then, an aggregation module was presented to differentiably merge the shape corners and implicit fields using a corner weight prediction. In addition, to help further shape reconstruction work on corners and details, we released a new dataset based on Shapenet models, named Shape-CornerNet, including 43784 3D shapes in 13 categories with detailed corner points. Afterward, we quantitatively and qualitatively evaluated our model on Shape-CornerNet. Our IMC-NET achieved state-of-the-art performance on Shape-CornerNet.