3DBooSTeR: 3D Body Shape and Texture Recovery

TL;DR

3DBooSTeR introduces a method for reconstructing complete textured 3D human body meshes from partial scans by decoupling shape and texture completion, utilizing neural networks and inpainting techniques validated on a dedicated dataset.

Contribution

It presents a novel two-step approach for 3D body shape and texture recovery from partial scans, combining shape deformation and texture inpainting.

Findings

Effective shape reconstruction via encoder-decoder network.

Successful texture inpainting on partial 3D scans.

Validated on 3DBodyTex.v2 dataset.

Abstract

We propose 3DBooSTeR, a novel method to recover a textured 3D body mesh from a textured partial 3D scan. With the advent of virtual and augmented reality, there is a demand for creating realistic and high-fidelity digital 3D human representations. However, 3D scanning systems can only capture the 3D human body shape up to some level of defects due to its complexity, including occlusion between body parts, varying levels of details, shape deformations and the articulated skeleton. Textured 3D mesh completion is thus important to enhance 3D acquisitions. The proposed approach decouples the shape and texture completion into two sequential tasks. The shape is recovered by an encoder-decoder network deforming a template body mesh. The texture is subsequently obtained by projecting the partial texture onto the template mesh before inpainting the corresponding texture map with a novel approach. The approach is validated on the 3DBodyTex.v2 dataset.