2 code implementations • 5 Dec 2023 • Xiaohu Lu, Hayder Radha
Universal adversarial attack methods such as Fast Sign Gradient Method (FSGM) and Projected Gradient Descend (PGD) are popular for LiDAR object detection, but they are often deficient compared to task-specific adversarial attacks.
no code implementations • 12 Sep 2023 • Xiaohu Lu, Hayder Radha
The extension from single-target to multi-target domain adaptation is accomplished by exploring the class-wise distance relationship between domains and replacing the strong representative set with much stronger samples from peer domains via peer scaffolding.
no code implementations • 1 Jul 2021 • Hessah Albanwan, Rongjun Qin, Xiaohu Lu, Mao Li, Desheng Liu, Jean-Michel Guldmann
The current practice in land cover/land use change analysis relies heavily on the individually classified maps of the multitemporal data set.
no code implementations • CVPR 2020 • Xiaohu Lu, Zuoyue Li, Zhaopeng Cui, Martin R. Oswald, Marc Pollefeys, Rongjun Qin
We present a novel method for generating panoramic street-view images which are geometrically consistent with a given satellite image.
no code implementations • 22 May 2019 • Bihe Chen, Rongjun Qin, Xu Huang, Shuang Song, Xiaohu Lu
Stereo dense image matching can be categorized to low-level feature based matching and deep feature based matching according to their matching cost metrics.
no code implementations • 22 May 2019 • Xiaohu Lu, Rong-Jun Qin, Xu Huang
Nowadays dense stereo matching has become one of the dominant tools in 3D reconstruction of urban regions for its low cost and high flexibility in generating dense 3D points.
3 code implementations • 8 Jan 2019 • Xiaohu Lu, Yahui Liu, Kai Li
This paper presents a very simple but efficient algorithm for 3D line segment detection from large scale unorganized point cloud.
no code implementations • 12 May 2017 • Yahui Liu, Jian Yao, Li Li, Xiaohu Lu, Jing Han
We develop a novel deep contour detection algorithm with a top-down fully convolutional encoder-decoder network.