no code implementations • 24 Sep 2021 • Tarek Ben Charrada, Hedi Tabia, Aladine Chetouani, Hamid Laga
It is composed of of (1) a Vertex Generation Network (VGN), which predicts the initial 3D locations of the object's vertices from an input RGB image, (2) a differentiable triangulation layer, which learns in a non-supervised manner, using a novel reinforcement learning algorithm, the best triangulation of the object's vertices, and finally, (3) a hierarchical mesh refinement network that uses graph convolutions to refine the initial mesh.