1 code implementation • 4 May 2024 • Shuai Yuan, Lei Luo, Zhuo Hui, Can Pu, Xiaoyu Xiang, Rakesh Ranjan, Denis Demandolx
Traditional unsupervised optical flow methods are vulnerable to occlusions and motion boundaries due to lack of object-level information.
1 code implementation • 10 May 2023 • Can Pu, Chuanyu Yang, Jinnian Pu, Radim Tylecek, Robert B. Fisher
Next, the refined disparity maps are converted into full-view point clouds or single-view point clouds for the pose fusion module.
no code implementations • 9 Feb 2023 • Can Pu, Chuanyu Yang, Jinnian Pu, Robert B. Fisher
More specifically, in the automation stage, the robot navigates to the specified location without the need of a precise parking.
1 code implementation • 2 Oct 2021 • Qiangqiang Huang, Can Pu, Kasra Khosoussi, David M. Rosen, Dehann Fourie, Jonathan P. How, John J. Leonard
This paper presents normalizing flows for incremental smoothing and mapping (NF-iSAM), a novel algorithm for inferring the full posterior distribution in SLAM problems with nonlinear measurement models and non-Gaussian factors.
no code implementations • 22 Apr 2019 • Can Pu, Robert B. Fisher
In this paper, a mathematical model for disparity fusion is proposed to guide an adversarial network to train effectively without ground truth disparity data.
2 code implementations • 18 Mar 2018 • Can Pu, Nanbo Li, Radim Tylecek, Robert B. Fisher
Existing rigid registration methods failed to use the physical 3D uncertainty distribution of each point from a real sensor in the dynamic alignment process mainly because the uncertainty model for a point is static and invariant and it is hard to describe the change of these physical uncertainty models in the registration process.
no code implementations • 18 Mar 2018 • Can Pu, Runzi Song, Radim Tylecek, Nanbo Li, Robert B. Fisher
into a refiner network to better refine raw disparity inputs.
no code implementations • 26 Jul 2017 • Can Pu, Nanbo Li, Robert B. Fisher
Matching 3D rigid point clouds in complex environments robustly and accurately is still a core technique used in many applications.