3D Holistic OR Anonymization

TL;DR

This paper introduces a 3D-based method for anonymizing multi-view RGB-D videos in operating rooms by localizing and replacing faces in 3D space, improving realism and accuracy over existing 2D methods.

Contribution

It presents a novel 3D face localization and anonymization technique for multi-view OR videos and introduces a new dataset captured during laparoscopic surgeries.

Findings

3D localization improves face detection accuracy in OR videos

Generated faces are more realistic compared to 2D methods

Method outperforms existing anonymization techniques in experiments

Abstract

We propose a novel method that leverages 3D information to automatically anonymize multi-view RGB-D video recordings of operating rooms (OR). Our anonymization method preserves the original data distribution by replacing the faces in each image with different faces so that the data remains suitable for further downstream tasks. In contrast to established anonymization methods, our approach localizes faces in 3D space first rather than in 2D space. Each face is then anonymized by reprojecting a different face back into each camera view, ultimately replacing the original faces in the resulting images. Furthermore, we introduce a multi-view RGB-D dataset, captured during a real operation of experienced surgeons performing laparoscopic surgery on an animal object (swine), which encapsulates typical characteristics of ORs. Finally, we present experimental results evaluated on that dataset, showing that leveraging 3D data can achieve better face localization in OR images and generate more realistic faces than the current state-of-the-art. There has been, to our knowledge, no prior work that addresses the anonymization of multi-view OR recordings, nor 2D face localization that leverages 3D information.