Learning-based Stereo Matching for 3D Reconstruction
Wednesday, May 16, 11 a.m.-12 p.m.
Talk given by Wendong Mao, Ph.D. student in the Department of Computer Science Abstract Stereo matching has been widely adopted for 3D reconstruction of real world scenes and has enormous applications in both military and civilian fields. Being an ill-posed problem, estimating accurate disparity maps is a challenging task. However, humans rely on binocular vision to perceive 3D environments and can estimate 3D information more rapidly and robustly than many active and passive sensors that have been developed. One of the reasons is that human brains can utilize prior knowledge to understand the scene and to infer the most reasonable depth hypothesis even when the visual cues are lacking. Recent advances in machine learning have shown that the brain’s discrimination power can be mimicked using deep convolutional neural networks (CNNs). Hence, a learning-based approach is proposed here to enhance traditional stereo matching algorithms for 3D reconstruction.
Presented by Department of Computer Science