1 citations · 1 across the 3 of their papers we have counts for
4 papers
Discriminately Treating Motion Components Evolves Joint Depth and Ego-Motion Learning
Mengtan Zhang, Zizhan Guo, Hongbo Zhao +6
Unsupervised learning of depth and ego-motion, two fundamental 3D perception tasks, has made significant strides in recent years. However, most methods treat ego-motion as an auxil…
DSGC-Net: A Dual-Stream Graph Convolutional Network for Crowd Counting via Feature Correlation Mining
Yihong Wu, Jinqiao Wei, Xionghui Zhao +4
Deep learning-based crowd counting methods have achieved remarkable progress in recent years. However, in complex crowd scenarios, existing models still face challenges when adapti…
Learning a Category-level Object Pose Estimator without Pose Annotations
Fengrui Tian, Yaoyao Liu, Adam Kortylewski +4
3D object pose estimation is a challenging task. Previous works always require thousands of object images with annotated poses for learning the 3D pose correspondence, which is lab…
Semantic Flow: Learning Semantic Field of Dynamic Scenes from Monocular Videos
Fengrui Tian, Yueqi Duan, Angtian Wang +2
In this work, we pioneer Semantic Flow, a neural semantic representation of dynamic scenes from monocular videos. In contrast to previous NeRF methods that reconstruct dynamic scen…