➣ Video Recoloring via Spatial-Temporal Geometric Palettes

Zheng-Jun Du, Kai-Xiang Lei, Kun Xu, Jianchao Tan, Yotam Gingold


We introduce a spatial-temporal geometry-based approach to video recoloring. Specifically, its core is a 4D skew polytope with a few vertices that approximately encloses the video pixels in color and time, which implicitly defines time-varying palettes through slicing of the 4D skew polytope at specific time values.


➣ Accurate Dynamic SLAM using CRF-based Long-term Consistency

Zheng-Jun Du, Shi-Sheng Huang, Tai-Jiang Mu, Qunhe Zhao, Ralph Martin, Kun Xu.

IEEE Transactions on Visualization and Computer Graphics (TVCG) 2020

We propose a novel RGB-D SLAM approach for accurate camera pose tracking in dynamic environments. We provide a more accurate dynamic 3D landmark detection method, followed by the use of long-term consistency via conditional random fields. Evaluation on the TUM and Bonn RGB-D dynamic datasets shows that their approach achieves state-of-the-art accuracy.