no code implementations • 17 Apr 2024 • Fei Cui, Jiaojiao Fang, Xiaojiang Wu, Zelong Lai, Mengke Yang, Menghan Jia, Guizhong Liu
In this paper, we propose a state-space decomposition stochastic video prediction model that decomposes the overall video frame generation into deterministic appearance prediction and stochastic motion prediction.
no code implementations • 30 Jun 2023 • Fei Cui, Jiaojiao Fang, Mengke Yang, Guizhong Liu
Goal-conditioned hierarchical reinforcement learning (GCHRL) decomposes long-horizon tasks into sub-tasks through a hierarchical framework and it has demonstrated promising results across a variety of domains.
no code implementations • 9 Aug 2021 • Jiaojiao Fang, Guizhong Liu
Self-supervised deep learning-based 3D scene understanding methods can overcome the difficulty of acquiring the densely labeled ground-truth and have made a lot of advances.
no code implementations • 4 Aug 2021 • Jiaojiao Fang, Guizhong Liu
To makes the optimization easier, we further incorporate the epipolar geometry into the ICP based learning process for pose learning.
no code implementations • 3 Sep 2019 • Lingtao Zhou, Jiaojiao Fang, Guizhong Liu
Unsupervised learning based depth estimation methods have received more and more attention as they do not need vast quantities of densely labeled data for training which are touch to acquire.
no code implementations • 1 Sep 2019 • Jiaojiao Fang, Lingtao Zhou, Guizhong Liu
In this paper, we propose a novel two stage 3D object detection method aimed at get the optimal solution of object location in 3D space based on regressing two additional 3D object properties by a deep convolutional neural network and combined with cascaded geometric constraints between the 2D and 3D boxes.