Layered-Garment Net: Generating Multiple Implicit Garment Layers from a Single Image

Recent research works have focused on generating human models and garments from their 2D images. However, state-of-the-art researches focus either only a single layer of the garment model or multiple layers without any guarantee intersection-free geometric relationship between them. In reality, people wear in daily life, where an inner could be partially covered by outer one. this paper, we try to address multi-layer modeling problem propose Layered-Garment Net (LGN) that is capable defined implicit function fields over body surface, given person’s near front-view image. With special design indication (GIF), can enforce covering signed distance (SDF) different avoid self-intersections among surfaces body. Experiments demonstrate strength our proposed LGN framework as compared methods. To best knowledge, first work generate