SALVE: A 3D Reconstruction Benchmark of Wounds from Consumer-grade Videos

TL;DR

This paper introduces the SALVE dataset and evaluates various 3D reconstruction methods from consumer videos, highlighting the limitations of photogrammetry and the potential of neural rendering for clinical wound assessment.

Contribution

The study provides a comprehensive evaluation of 3D wound reconstruction techniques using a new dataset, advancing understanding of their suitability for clinical applications.

Findings

Photogrammetry methods produce non-smooth wound surfaces.

Neural rendering approaches show potential for accurate wound modeling.

The SALVE dataset enables benchmarking of 3D reconstruction techniques.

Abstract

Managing chronic wounds is a global challenge that can be alleviated by the adoption of automatic systems for clinical wound assessment from consumer-grade videos. While 2D image analysis approaches are insufficient for handling the 3D features of wounds, existing approaches utilizing 3D reconstruction methods have not been thoroughly evaluated. To address this gap, this paper presents a comprehensive study on 3D wound reconstruction from consumer-grade videos. Specifically, we introduce the SALVE dataset, comprising video recordings of realistic wound phantoms captured with different cameras. Using this dataset, we assess the accuracy and precision of state-of-the-art methods for 3D reconstruction, ranging from traditional photogrammetry pipelines to advanced neural rendering approaches. In our experiments, we observe that photogrammetry approaches do not provide smooth surfaces suitable for precise clinical measurements of wounds. Neural rendering approaches show promise in addressing this issue, advancing the use of this technology in wound care practices. We encourage the readers to visit the project page: https://remichierchia.github.io/SALVE/.