Deep Motion Flow Estimation for Monocular Endoscope

For monocular endoscope motion estimation, traditional algorithms often suffer from poor robustness when encountering uninformative or dark frames since they only use prominent image features. In contrast, deep learning methods based on an end-to-end framework have achieved promising performance by estimating the 6-DOF pose directly. However, the existing techniques overly depend on the mass high-precision labelled 6-DOF pose data, which is difficult to obtain in practical scenarios. In this work, we propose a fast yet robust method for monocular endoscope motion estimation named Deep Motion Flow Estimation (DMFE). Specifically, we propose an innovative Key Points Encoder (KPE) supervised by Speeded-up Robust Features (SURF) flow to extract the salient features of endoscopic images. Aiming to ensure real-time capability, we propose a novel 3D motion transfer algorithm to reduce the computational complexity of the essential matrix. Extensive experiments on clinical and virtual colon datasets demonstrate the superiority of our method against the traditional methods, which can provide visual navigation assistance for doctors or robotic endoscopes in real-world scenarios.