Supplementary Material for DDF-HO: Hand-Held Object Reconstruction via Conditional Directed Distance Field 1 Network Architecture

After 2D ray sampling process depicted in Sec. The total number of parameters of our network is 25M. In Section 3.4 of the main manuscript, we introduce the 3D intersection-aware hand feature This process enables the extraction of global information from the hand joints. Our training process involves the utilization of five distinct types of data samples. In this section, we provide the corresponding table (Tab.