Robust Real-Time Endoscopic Stereo Matching under Fuzzy Tissue Boundaries
This addresses the need for accurate, real-time depth information in automated robotic surgery, though it appears to be an incremental improvement over existing stereo matching methods adapted to a specific domain.
The paper tackles the problem of real-time depth estimation in robotic minimally invasive surgery by developing RRESM, a stereo matching method specifically designed for endoscopic images with fuzzy tissue boundaries. The method achieves state-of-the-art matching accuracy on SCARED and SERV-CT datasets while running at 42 FPS.
Real-time acquisition of accurate scene depth is essential for automated robotic minimally invasive surgery. Stereo matching with binocular endoscopy can provide this depth information. However, existing stereo matching methods, designed primarily for natural images, often struggle with endoscopic images due to fuzzy tissue boundaries and typically fail to meet real-time requirements for high-resolution endoscopic image inputs. To address these challenges, we propose \textbf{RRESM}, a real-time stereo matching method tailored for endoscopic images. Our approach integrates a 3D Mamba Coordinate Attention module that enhances cost aggregation through position-sensitive attention maps and long-range spatial dependency modeling via the Mamba block, generating a robust cost volume without substantial computational overhead. Additionally, we introduce a High-Frequency Disparity Optimization module that refines disparity predictions near tissue boundaries by amplifying high-frequency details in the wavelet domain. Evaluations on the SCARED and SERV-CT datasets demonstrate state-of-the-art matching accuracy with a real-time inference speed of 42 FPS. The code is available at https://github.com/Sonne-Ding/RRESM.