DoubleFusion: Real-time Capture of Human Performances with Inner Body Shapes from a Single Depth Sensor

TL;DR

DoubleFusion is a real-time system that reconstructs detailed human body geometry, motion, and inner shape from a single depth sensor using a double layer volumetric representation and data-driven fitting.

Contribution

It introduces a novel double layer representation combining a parametric inner body shape with an outer surface, enabling detailed and robust real-time reconstruction from a single depth camera.

Findings

Improved real-time motion tracking accuracy.

Enhanced surface detail and completeness in reconstructions.

Robust inner body shape estimation in challenging scenarios.

Abstract

We propose DoubleFusion, a new real-time system that combines volumetric dynamic reconstruction with data-driven template fitting to simultaneously reconstruct detailed geometry, non-rigid motion and the inner human body shape from a single depth camera. One of the key contributions of this method is a double layer representation consisting of a complete parametric body shape inside, and a gradually fused outer surface layer. A pre-defined node graph on the body surface parameterizes the non-rigid deformations near the body, and a free-form dynamically changing graph parameterizes the outer surface layer far from the body, which allows more general reconstruction. We further propose a joint motion tracking method based on the double layer representation to enable robust and fast motion tracking performance. Moreover, the inner body shape is optimized online and forced to fit inside the outer surface layer. Overall, our method enables increasingly denoised, detailed and complete surface reconstructions, fast motion tracking performance and plausible inner body shape reconstruction in real-time. In particular, experiments show improved fast motion tracking and loop closure performance on more challenging scenarios.