Fully Convolutional Graph Neural Networks for Parametric Virtual Try-On

Abstract

Figure 1: Our method predicts the 3D draping for an arbitrary body shape and garment parameters at interactive rates. From left to right, a variety of body shapes obtained from a parametric avatar model, different 2D panel configurations of our paremeterized garment types, and corresponding dressed 3D bodies generated with our novel fully convolutional approach.

Shape Controllable Virtual Try-on for Underwear Models

“…3D virtual try-on systems based on human reconstruction in computer graphics have been widely researched, such as [1,3,27,30,44]. While Physics-Based Simulation (PBS) can accurately drape a 3D garment on a 3D body [12,33,40,46], it remains too costly for real-time applications. 3D human estimation methods try to digitalize real-world 2D character photos to 3D models, which have made significant progress after the popularity of deep learning, such as [10,22,25,52], while [13,21,38,39] also digitizing with garments, these methods still need to be optimized in texture authenticity.…”

“…Based on [48], Wen et al [49] used GCN to solve the problem of shape generation in 3D mesh representation from a few color images with known camera poses. For the virtual try-on task, Vidaurre [46] used GCN for parametric predefined 2D panels with arbitrary mesh topology. Kolotouros et al [25] adopted a Graph-CNN to estimate 3D human pose and shape from a single image.…”