activity
20192022
most citedBeyond Tracking: Selecting Memory and Refining Poses for Deep Visual Odometry

14 citations · 21 across the 4 of their papers we have counts for

collaborators

5 papers

cs.CV2022

SC-wLS: Towards Interpretable Feed-forward Camera Re-localization

Xin Wu, Hao Zhao, Shunkai Li +2

Visual re-localization aims to recover camera poses in a known environment, which is vital for applications like robotics or augmented reality. Feed-forward absolute camera pose re…

cs.CV20212 cited

Generalizing to the Open World: Deep Visual Odometry with Online Adaptation

Shunkai Li, Xin Wu, Yingdian Cao +1

Despite learning-based visual odometry (VO) has shown impressive results in recent years, the pretrained networks may easily collapse in unseen environments. The large domain gap b…

cs.CV20205 cited

Self-Supervised Deep Visual Odometry with Online Adaptation

Shunkai Li, Xin Wang, Yingdian Cao +3

Self-supervised VO methods have shown great success in jointly estimating camera pose and depth from videos. However, like most data-driven methods, existing VO networks suffer fro…

cs.CV2019

Sequential Adversarial Learning for Self-Supervised Deep Visual Odometry

Shunkai Li, Fei Xue, Xin Wang +2

We propose a self-supervised learning framework for visual odometry (VO) that incorporates correlation of consecutive frames and takes advantage of adversarial learning. Previous m…

cs.CV201914 cited

Beyond Tracking: Selecting Memory and Refining Poses for Deep Visual Odometry

Fei Xue, Xin Wang, Shunkai Li +3

Most previous learning-based visual odometry (VO) methods take VO as a pure tracking problem. In contrast, we present a VO framework by incorporating two additional components call…