Benchmarking Robustness of Endoscopic Depth Estimation with Synthetically Corrupted Data
An Wang, Haochen Yin, Beilei Cui, Mengya Xu, Hongliang Ren
TL;DR
This work tackles robust monocular depth estimation in endoscopic surgery under realistic image corruptions. It introduces the SCARED-C dataset, a corruption-augmented extension of SCARED, and the Depth Estimation Robustness Score (DERS), a composite metric that integrates error, accuracy, and robustness via $DERS = \frac{E}{A} e^{-R}$ with constituent definitions for $E$, $A$, and $R$. Using two self-supervised monocular methods, MonoDepth2 and AF-SfMLearner, the study demonstrates that corruption type and severity distinctly affect depth predictions, and that DERS captures these variations to compare model resilience. The benchmark and accompanying code provide a practical framework for guiding the development of more robust depth estimation in surgical settings, with potential to improve precision and patient safety.
Abstract
Accurate depth perception is crucial for patient outcomes in endoscopic surgery, yet it is compromised by image distortions common in surgical settings. To tackle this issue, our study presents a benchmark for assessing the robustness of endoscopic depth estimation models. We have compiled a comprehensive dataset that reflects real-world conditions, incorporating a range of synthetically induced corruptions at varying severity levels. To further this effort, we introduce the Depth Estimation Robustness Score (DERS), a novel metric that combines measures of error, accuracy, and robustness to meet the multifaceted requirements of surgical applications. This metric acts as a foundational element for evaluating performance, establishing a new paradigm for the comparative analysis of depth estimation technologies. Additionally, we set forth a benchmark focused on robustness for the evaluation of depth estimation in endoscopic surgery, with the aim of driving progress in model refinement. A thorough analysis of two monocular depth estimation models using our framework reveals crucial information about their reliability under adverse conditions. Our results emphasize the essential need for algorithms that can tolerate data corruption, thereby advancing discussions on improving model robustness. The impact of this research transcends theoretical frameworks, providing concrete gains in surgical precision and patient safety. This study establishes a benchmark for the robustness of depth estimation and serves as a foundation for developing more resilient surgical support technologies. Code is available at https://github.com/lofrienger/EndoDepthBenchmark.