Self-Supervised Monocular Depth and Ego-Motion Estimation in Endoscopy: Appearance Flow to the Rescue
This work addresses a critical challenge in medical imaging for endoscopy by improving accuracy in 3D reconstruction and navigation, though it is incremental as it builds on existing self-supervised methods.
The paper tackles the problem of inaccurate depth and ego-motion estimation in endoscopic scenes due to brightness fluctuations, by introducing appearance flow to address brightness inconsistency and building a unified self-supervised framework, achieving superior results on datasets like SCARED and EndoSLAM with strong generalization to other datasets without fine-tuning.
Recently, self-supervised learning technology has been applied to calculate depth and ego-motion from monocular videos, achieving remarkable performance in autonomous driving scenarios. One widely adopted assumption of depth and ego-motion self-supervised learning is that the image brightness remains constant within nearby frames. Unfortunately, the endoscopic scene does not meet this assumption because there are severe brightness fluctuations induced by illumination variations, non-Lambertian reflections and interreflections during data collection, and these brightness fluctuations inevitably deteriorate the depth and ego-motion estimation accuracy. In this work, we introduce a novel concept referred to as appearance flow to address the brightness inconsistency problem. The appearance flow takes into consideration any variations in the brightness pattern and enables us to develop a generalized dynamic image constraint. Furthermore, we build a unified self-supervised framework to estimate monocular depth and ego-motion simultaneously in endoscopic scenes, which comprises a structure module, a motion module, an appearance module and a correspondence module, to accurately reconstruct the appearance and calibrate the image brightness. Extensive experiments are conducted on the SCARED dataset and EndoSLAM dataset, and the proposed unified framework exceeds other self-supervised approaches by a large margin. To validate our framework's generalization ability on different patients and cameras, we train our model on SCARED but test it on the SERV-CT and Hamlyn datasets without any fine-tuning, and the superior results reveal its strong generalization ability. Code will be available at: \url{https://github.com/ShuweiShao/AF-SfMLearner}.