Best Foot Forward: Robust Foot Reconstruction in-the-wild

TL;DR

This paper introduces a robust end-to-end pipeline for 3D foot reconstruction in real-world scenarios, combining viewpoint prediction and attention-based completion to improve accuracy and anatomical fidelity.

Contribution

It presents a novel method that refines SfM reconstruction with viewpoint canonicalization and learned geometry completion, addressing incomplete scans and anatomical variations.

Findings

Achieves state-of-the-art reconstruction metrics

Preserves clinically validated anatomical features

Enables robust mobile-based 3D foot scanning

Abstract

Accurate 3D foot reconstruction is crucial for personalized orthotics, digital healthcare, and virtual fittings. However, existing methods struggle with incomplete scans and anatomical variations, particularly in self-scanning scenarios where user mobility is limited, making it difficult to capture areas like the arch and heel. We present a novel end-to-end pipeline that refines Structure-from-Motion (SfM) reconstruction. It first resolves scan alignment ambiguities using SE(3) canonicalization with a viewpoint prediction module, then completes missing geometry through an attention-based network trained on synthetically augmented point clouds. Our approach achieves state-of-the-art performance on reconstruction metrics while preserving clinically validated anatomical fidelity. By combining synthetic training data with learned geometric priors, we enable robust foot reconstruction under real-world capture conditions, unlocking new opportunities for mobile-based 3D scanning in healthcare and retail.