StereoMamba architecture enhances real-time stereo disparity estimation for robotic surgery

Researchers have developed StereoMamba, a novel architecture for real-time stereo disparity estimation in robot-assisted surgery. This system utilizes a Feature Extraction Mamba module to capture long-range spatial dependencies and a Multidimensional Feature Fusion module for integrating multi-scale features. StereoMamba demonstrates strong performance on benchmarks like SCARED, achieving a balance between accuracy, robustness, and a speed of over 21 FPS for high-resolution images. AI

影响 Introduces a new architecture for real-time depth estimation in surgical robotics, potentially improving surgical precision and outcomes.

排序理由 This is a research paper detailing a new model architecture for a specific computer vision task. [lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CV 阅读 →

• Mamba
• RIS2017
• StereoMamba
• StereoMIS
• Xu Wang

• 论文
• 其他

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →