3D High-quality Garment Reconstruction with Synthesized Texture

Abstract

3D garment model plays an important role in the fashion industry. However, not much work focus on extracting high-quality clothes from scanned data. The texture is limited by photography methods in 3D scanning. This paper proposes a novel framework of reconstructing high-quality 3D garment models with synthesized texture. Firstly, a pipeline of 3D garment processing is proposed to obtain a better 3D model based on KinectFusion. Then, DeepTextures is used to synthesize a new texture. To our best knowledge, this is the first paper combining 3D garment reconstruction and texture synthesis. Experimental results show that our method can conveniently obtain 3D garment models and realistic textures.