IGE-Net: Inverse graphics energy networks for human pose estimation and single-view reconstruction

Dominic Jack, Frederic Maire, Sareh Rowlands, Anders Eriksson

Abstract:

Inferring 3D scene information from 2D observations
is an open problem in computer vision. We propose using a deep-learning based energy minimization framework
to learn a consistency measure between 2D observations
and a proposed world model, and demonstrate that this
framework can be trained end-to-end to produce consistent and realistic inferences. We evaluate the framework
on human pose estimation and voxel-based object reconstruction benchmarks and show competitive results can be
achieved with relatively shallow networks with drastically
fewer learned parameters and floating point operations
than conventional deep-learning approaches.