no code implementations • 5 Dec 2024 • Haitian Zhang, Xiangyuan Wang, Chang Xu, Xinya Wang, Fang Xu, Huai Yu, Lei Yu, Wen Yang
We further propose a training strategy, Time Shift, which enforces the module to align the prediction from temporally shifted Event-RGB pairs and their original representation, that is, consistent with Event-aligned annotations.
no code implementations • 4 Dec 2024 • Ji Wu, Huai Yu, Shu Han, Xi-Meng Cai, Ming-Feng Wang, Wen Yang, Gui-Song Xia
In the realm of large-scale point cloud registration, designing a compact symbolic representation is crucial for efficiently processing vast amounts of data, ensuring registration robustness against significant viewpoint variations and occlusions.
no code implementations • 22 Nov 2024 • Haoyuan Li, Chang Xu, Wen Yang, Li Mi, Huai Yu, Haijian Zhang
As such, our unsupervised paradigm naturally avoids the problem of region-specific overfitting, enabling generic CVGL for UAV images without feature fine-tuning or data-driven training.
no code implementations • 19 Mar 2024 • Haoyuan Li, Chang Xu, Wen Yang, Huai Yu, Gui-Song Xia
We observe that training on unlabeled cross-view images presents significant challenges, including the need to establish relationships within unlabeled data and reconcile view discrepancies between uncertain queries and references.
no code implementations • 23 Oct 2023 • Ruixiang Zhang, Chang Xu, Fang Xu, Wen Yang, Guangjun He, Huai Yu, Gui-Song Xia
This paper focuses on the scale imbalance problem of semi-supervised object detection(SSOD) in aerial images.
1 code implementation • 25 Sep 2023 • Ji Wu, Huai Yu, Wen Yang, Gui-Song Xia
This paper presents a novel framework to learn a concise geometric primitive representation for 3D point clouds.
1 code implementation • CVPR 2023 • Chang Xu, Jian Ding, Jinwang Wang, Wen Yang, Huai Yu, Lei Yu, Gui-Song Xia
Despite the exploration of adaptive label assignment in recent oriented object detectors, the extreme geometry shape and limited feature of oriented tiny objects still induce severe mismatch and imbalance issues.
Ranked #4 on
Oriented Object Detection
on DOTA 2.0
no code implementations • 6 Dec 2022 • Zhipeng Zhao, Huai Yu, Chenwei Lyv, Wen Yang, Sebastian Scherer
To overcome this limitation, we focus on correlating the information of 360 equirectangular images to point clouds, proposing an end-to-end learnable network to conduct cross-modal visual localization by establishing similarity in high-dimensional feature space.
1 code implementation • 14 Nov 2022 • Huai Yu, Hao Li, Wen Yang, Lei Yu, Gui-Song Xia
To robustly detect line segments over motion blurs, we propose to leverage the complementary information of images and events.
no code implementations • 2 Oct 2022 • Xinhang Liu, Jiaben Chen, Huai Yu, Yu-Wing Tai, Chi-Keung Tang
The core of our method is a novel propagation strategy for individual objects' radiance fields with a bidirectional photometric loss, enabling an unsupervised partitioning of a scene into salient or meaningful regions corresponding to different object instances.
1 code implementation • 24 Aug 2022 • Bingde Liu, Chang Xu, Wen Yang, Huai Yu, Lei Yu
In this work, we propose a motion robust and high-speed detection pipeline which better leverages the event data.
1 code implementation • 18 Aug 2022 • Chang Xu, Jinwang Wang, Wen Yang, Huai Yu, Lei Yu, Gui-Song Xia
Then, instead of assigning samples with IoU or center sampling strategy, a new Receptive Field Distance (RFD) is proposed to directly measure the similarity between the Gaussian receptive field and ground truth.
Ranked #2 on
Object Detection
on AI-TOD
1 code implementation • 28 Jun 2022 • Chang Xu, Jinwang Wang, Wen Yang, Huai Yu, Lei Yu, Gui-Song Xia
Tiny object detection (TOD) in aerial images is challenging since a tiny object only contains a few pixels.
no code implementations • 20 Aug 2021 • Weikun Zhen, Huai Yu, Yaoyu Hu, Sebastian Scherer
We first present a unified representation based on quadrics, leading to a consistent and concise formulation.
no code implementations • 13 Mar 2021 • Yaoyu Hu, Wenshan Wang, Huai Yu, Weikun Zhen, Sebastian Scherer
Stereo reconstruction models trained on small images do not generalize well to high-resolution data.
2 code implementations • 6 Nov 2020 • Hao Li, Huai Yu, Wen Yang, Lei Yu, Sebastian Scherer
Targeting at the unified line segment detection (ULSD) for both distorted and undistorted images, we propose to represent line segments with the Bezier curve model.
Ranked #5 on
Line Segment Detection
on wireframe dataset
(sAP10 metric)
1 code implementation • 1 Apr 2020 • Huai Yu, Weikun Zhen, Wen Yang, Ji Zhang, Sebastian Scherer
With the pose prediction from VIO, we can efficiently obtain coarse 2D-3D line correspondences.
no code implementations • 23 Nov 2019 • Huai Yu, Weikun Zhen, Wen Yang, Sebastian Scherer
In this paper, we propose a new 2D-3D registration method to estimate 2D-3D line feature correspondences and the camera pose in untextured point clouds of structured environments.