Wenzhe Yang

2 accepted papers

2023

VI-HSO: Hybrid Sparse Monocular Visual-Inertial Odometry

Wenzhe Yang, Yan Zhuang, Dongting Luo, Wei Wang, Hong Zhang

RA-L 2023

In this letter, we present VI-HSO, a hybrid sparse monocular visual-inertial odometry system based on two innovative techniques called adaptive interframe alignment (AIA) and dynamic inverse distance filter (DIDF). Although the sparse image alignment algorithm appears efficient for calculating frame

Cited by 2 Source ↗Scholar ↗

2021

Deep Homography for Efficient Stereo Image Compression

Xin Deng, Wenzhe Yang, Ren Yang, Mai Xu, Enpeng Liu, Qianhan Feng +1

CVPR 2021poster

In this paper, we propose HESIC, an end-to-end trainable deep network for stereo image compression (SIC). To fully explore the mutual information across two stereo images, we use a deep regression model to estimate the homography matrix, i.e., H matrix. Then, the left image is spatially transformed…

Cited by 54 PDF ↗code ↗Scholar ↗