FIND: An Unsupervised Implicit 3D Model of Articulated Human Feet

TL;DR

This paper introduces FIND, an unsupervised neural model for high-fidelity, articulated 3D human foot reconstruction that works with minimal supervision and includes a new dataset, Foot3D.

Contribution

We develop a neural deformation model for 3D feet, propose weakly supervised training methods, and introduce an unsupervised part-based loss for better image fitting.

Findings

FIND outperforms PCA in shape quality and part correspondence.

The model effectively learns with limited supervision.

The new loss improves image inference accuracy.

Abstract

In this paper we present a high fidelity and articulated 3D human foot model. The model is parameterised by a disentangled latent code in terms of shape, texture and articulated pose. While high fidelity models are typically created with strong supervision such as 3D keypoint correspondences or pre-registration, we focus on the difficult case of little to no annotation. To this end, we make the following contributions: (i) we develop a Foot Implicit Neural Deformation field model, named FIND, capable of tailoring explicit meshes at any resolution i.e. for low or high powered devices; (ii) an approach for training our model in various modes of weak supervision with progressively better disentanglement as more labels, such as pose categories, are provided; (iii) a novel unsupervised part-based loss for fitting our model to 2D images which is better than traditional photometric or silhouette losses; (iv) finally, we release a new dataset of high resolution 3D human foot scans, Foot3D. On this dataset, we show our model outperforms a strong PCA implementation trained on the same data in terms of shape quality and part correspondences, and that our novel unsupervised part-based loss improves inference on images.