Representing a Partially Observed Non-Rigid 3D Human Using Eigen-Texture and Eigen-Deformation

TL;DR

This paper introduces a novel method for reconstructing and visualizing full-body 3D human models with loose clothing from partial RGB-D data by using eigen-texture and eigen-deformation embeddings, enhanced with neural networks.

Contribution

It proposes a new approach combining eigen-decomposition and neural networks to synthesize textures and deformations for full-body reconstruction from partial observations.

Findings

Effective in reconstructing unobserved surfaces with loose clothing.

Works on both simulated and real data.

Demonstrates improved view synthesis of 3D human models.

Abstract

Reconstruction of the shape and motion of humans from RGB-D is a challenging problem, receiving much attention in recent years. Recent approaches for full-body reconstruction use a statistic shape model, which is built upon accurate full-body scans of people in skin-tight clothes, to complete invisible parts due to occlusion. Such a statistic model may still be fit to an RGB-D measurement with loose clothes but cannot describe its deformations, such as clothing wrinkles. Observed surfaces may be reconstructed precisely from actual measurements, while we have no cues for unobserved surfaces. For full-body reconstruction with loose clothes, we propose to use lower dimensional embeddings of texture and deformation referred to as eigen-texturing and eigen-deformation, to reproduce views of even unobserved surfaces. Provided a full-body reconstruction from a sequence of partial measurements as 3D meshes, the texture and deformation of each triangle are then embedded using eigen-decomposition. Combined with neural-network-based coefficient regression, our method synthesizes the texture and deformation from arbitrary viewpoints. We evaluate our method using simulated data and visually demonstrate how our method works on real data.