BodyNet: Volumetric Inference of 3D Human Body Shapes

TL;DR

BodyNet is a neural network that directly infers 3D human body shapes from a single image using volumetric and multi-view losses, achieving state-of-the-art results and enabling body-part segmentation.

Contribution

It introduces an end-to-end trainable volumetric inference method for 3D human shape estimation from images, bypassing traditional parametric models.

Findings

Achieves state-of-the-art results on SURREAL and Unite the People datasets.

Enables volumetric body-part segmentation.

Outperforms recent approaches in 3D human shape estimation.

Abstract

Human shape estimation is an important task for video editing, animation and fashion industry. Predicting 3D human body shape from natural images, however, is highly challenging due to factors such as variation in human bodies, clothing and viewpoint. Prior methods addressing this problem typically attempt to fit parametric body models with certain priors on pose and shape. In this work we argue for an alternative representation and propose BodyNet, a neural network for direct inference of volumetric body shape from a single image. BodyNet is an end-to-end trainable network that benefits from (i) a volumetric 3D loss, (ii) a multi-view re-projection loss, and (iii) intermediate supervision of 2D pose, 2D body part segmentation, and 3D pose. Each of them results in performance improvement as demonstrated by our experiments. To evaluate the method, we fit the SMPL model to our network output and show state-of-the-art results on the SURREAL and Unite the People datasets, outperforming recent approaches. Besides achieving state-of-the-art performance, our method also enables volumetric body-part segmentation.