Sparse RGB-D images create a real thing: A flexible voxel based 3D reconstruction pipeline for single object

Fei Luo, Yongqiong Zhu, Yanping Fu, Huajian Zhou, Zezheng Chen, Chunxia Xiao

Abstract: Highlights•We propose a voxel-based pipeline to reconstruct 3D model for single object with sparse RGB-D images. It can be flexibly used in different conditions and for popular RGB-D cameras.•A voxel-clipping operation is proposed to remove redundant voxels. Also, a voxel-filling operation is proposed to fill holes on surface.•Besides making the 3D geometric model more complete and precise, texture mapping is specially optimized in this work.