Abstract: Accurate and real-time disparity estimation from stereo images is crucial for many intelligent applications, such as autonomous driving, robotic navigation, and augmented reality. Although ...
Welcome to the L2M repository! This is the official implementation of our ICCV'25 paper titled "Learning Dense Feature Matching via Lifting Single 2D Image to 3D Space". To enable training from single ...
Abstract: Traditional stereo matching algorithms like SemiGlobal Block Matching (SGBM) with Weighted Least Squares (WLS) filtering offer speed advantages over neural networks for UAV applications, ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results