The goal of this paper is to learn dense 3D shape correspondence for topology-varying objects in an unsupervised manner. Our method is trained in three stages: 1) PointNet like encoder and implicit ...
Abstract: Recently, the single image super-resolution based on implicit image function is a hot topic, which learns a universal model for arbitrary upsampling scales. By contrast, color-guided depth ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results