FOCUS -- Multi-View Foot Reconstruction From Synthetically Trained Dense Correspondences

TL;DR

FOCUS introduces a multi-view human foot reconstruction method using synthetic data, dense correspondence prediction, and two reconstruction techniques, achieving state-of-the-art results with fewer views and faster processing.

Contribution

The paper presents SynFoot2 dataset, an uncertainty-aware dense correspondence predictor, and two novel 3D reconstruction methods for human foot modeling from multi-view images.

Findings

State-of-the-art quality with few views

Comparable performance with many views

Faster reconstruction process

Abstract

Surface reconstruction from multiple, calibrated images is a challenging task - often requiring a large number of collected images with significant overlap. We look at the specific case of human foot reconstruction. As with previous successful foot reconstruction work, we seek to extract rich per-pixel geometry cues from multi-view RGB images, and fuse these into a final 3D object. Our method, FOCUS, tackles this problem with 3 main contributions: (i) SynFoot2, an extension of an existing synthetic foot dataset to include a new data type: dense correspondence with the parameterized foot model FIND; (ii) an uncertainty-aware dense correspondence predictor trained on our synthetic dataset; (iii) two methods for reconstructing a 3D surface from dense correspondence predictions: one inspired by Structure-from-Motion, and one optimization-based using the FIND model. We show that our reconstruction achieves state-of-the-art reconstruction quality in a few-view setting, performing comparably to state-of-the-art when many views are available, and runs substantially faster. We release our synthetic dataset to the research community. Code is available at: https://github.com/OllieBoyne/FOCUS