activity
20192026
most citedDetecting tiny objects in aerial images: A normalized Wasserstein distance and a new benchmark

415 citations · 477 across the 25 of their papers we have counts for

collaborators
Showing 2022Show all

6 papers · 1 filter

cs.CV2022★ 1 cited

Attention-Enhanced Cross-modal Localization Between 360 Images and Point Clouds

Zhipeng Zhao, Huai Yu, Chenwei Lyv +2

Visual localization plays an important role for intelligent robots and autonomous driving, especially when the accuracy of GNSS is unreliable. Recently, camera localization in LiDA…

cs.CV2022

Detecting Line Segments in Motion-blurred Images with Events

Huai Yu, Hao Li, Wen Yang +2

Making line segment detectors more reliable under motion blurs is one of the most important challenges for practical applications, such as visual SLAM and 3D reconstruction. Existi…

cs.CV2022★ 6 cited

Unsupervised Multi-View Object Segmentation Using Radiance Field Propagation

Xinhang Liu, Jiaben Chen, Huai Yu +2

We present radiance field propagation (RFP), a novel approach to segmenting objects in 3D during reconstruction given only unlabeled multi-view images of a scene. RFP is derived fr…

cs.RO2022★ 36 cited

PyPose: A Library for Robot Learning with Physics-based Optimization

Chen Wang, Dasong Gao, Kuan Xu +34

Deep learning has had remarkable success in robotic perception, but its data-centric nature suffers when it comes to generalizing to ever-changing environments. By contrast, physic…

cs.CV2022★ 10 cited

RFLA: Gaussian Receptive Field based Label Assignment for Tiny Object Detection

Chang Xu, Jinwang Wang, Wen Yang +3

Detecting tiny objects is one of the main obstacles hindering the development of object detection. The performance of generic object detectors tends to drastically deteriorate on t…

cs.CV2022★ 415 cited

Detecting tiny objects in aerial images: A normalized Wasserstein distance and a new benchmark

Chang Xu, Jinwang Wang, Wen Yang +3

Tiny object detection (TOD) in aerial images is challenging since a tiny object only contains a few pixels. State-of-the-art object detectors do not provide satisfactory results on…