4 papers · 1 filter
Decoupled Object-Centric Video Understanding for Generating Robotic Manipulation Commands
Thanh Nguyen Canh, Thanh-Tuan Tran, Haolan Zhang +3
Translating video demonstrations into executable robot commands remains challenging because existing methods often fail to identify which objects are functionally involved in the d…
Con-DSO: Learning Short-Horizon Consistency Priors for RGB-D Direct Sparse Odometry
Haolan Zhang, Thanh Nguyen Canh, Chenghao Li +3
Visual odometry (VO) is a fundamental component in robotics and augmented reality. RGB-D direct VO benefits from metric depth measurements, but it can degrade in challenging enviro…
HMAFlow: Learning More Accurate Optical Flow via Hierarchical Motion Field Alignment
Dianbo Ma, Kousuke Imamura, Ziyan Gao +2
Optical flow estimation is a fundamental and long-standing visual task. In this work, we present a novel method, dubbed HMAFlow, to improve optical flow estimation in challenging s…
Staged Depthwise Correlation and Feature Fusion for Siamese Object Tracking
Dianbo Ma, Jianqiang Xiao, Ziyan Gao +1
In this work, we propose a novel staged depthwise correlation and feature fusion network, named DCFFNet, to further optimize the feature extraction for visual tracking. We build ou…