模糊组织边界下的鲁棒实时内窥镜立体匹配
Robust Real-Time Endoscopic Stereo Matching under Fuzzy Tissue Boundaries
AI总结：
针对内窥镜图像模糊边界导致现有立体匹配方法精度低、速度慢的问题，提出RRESM方法，集成3D Mamba坐标注意力和高频视差优化模块，在SCARED和SERV-CT数据集上达到最先进精度并以42 FPS实时运行。
摘要：
实时获取准确的场景深度对于自动化机器人微创手术至关重要。利用双目内窥镜进行立体匹配可以提供这种深度信息。然而，现有的立体匹配方法主要针对自然图像设计，在处理内窥镜图像时，由于组织边界模糊，往往表现不佳，并且通常无法满足高分辨率内窥镜图像输入的实时性要求。为了解决这些挑战，我们提出了RRESM，一种专为内窥镜图像定制的实时立体匹配方法。我们的方法集成了一个3D Mamba坐标注意力模块，该模块通过位置敏感注意力图和Mamba块的长距离空间依赖建模来增强代价聚合，在不产生大量计算开销的情况下生成稳健的代价体。此外，我们引入了一个高频视差优化模块，通过在波域中放大高频细节来细化组织边界附近的视差预测。在SCARED和SERV-CT数据集上的评估表明，我们的方法达到了最先进的匹配精度，并实现了42 FPS的实时推理速度。代码可在https://github.com/Sonne-Ding/RRESM获取。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
