iMatching: Imperative Correspondence Learning

no code implementations • 4 Dec 2023 • Zitong Zhan, Dasong Gao, Yun-Jou Lin, Youjie Xia, Chen Wang

Learning feature correspondence is a foundational task in computer vision, holding immense importance for downstream applications such as visual odometry and 3D reconstruction.

3D Reconstruction Bilevel Optimization +2

AirIMU: Learning Uncertainty Propagation for Inertial Odometry

1 code implementation • 7 Oct 2023 • Yuheng Qiu, Chen Wang, Can Xu, Yutian Chen, Xunfei Zhou, Youjie Xia, Sebastian Scherer

In contrast, data-driven IO methods struggle to accurately model the sensor motions, often leading to generalizability and interoperability issues.