activity
20192022
most citedUnsupervised Multi-View Object Segmentation Using Radiance Field Propagation

6 citations · 11 across the 7 of their papers we have counts for

collaborators

8 papers

cs.CV20226 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.RO20211 cited

Toward Efficient and Robust Multiple Camera Visual-inertial Odometry

Yao He, Huai Yu, Wen Yang +1

Efficiency and robustness are the essential criteria for the visual-inertial odometry (VIO) system. To process massive visual data, the high cost on CPU resources and computation l…

cs.RO2021

Unified Representation of Geometric Primitives for Graph-SLAM Optimization Using Decomposed Quadrics

Weikun Zhen, Huai Yu, Yaoyu Hu +1

In Simultaneous Localization And Mapping (SLAM) problems, high-level landmarks have the potential to build compact and informative maps compared to traditional point-based landmark…

cs.CV20211 cited

ORStereo: Occlusion-Aware Recurrent Stereo Matching for 4K-Resolution Images

Yaoyu Hu, Wenshan Wang, Huai Yu +2

Stereo reconstruction models trained on small images do not generalize well to high-resolution data. Training a model on high-resolution image size faces difficulties of data avail…

cs.CV20201 cited

ULSD: Unified Line Segment Detection across Pinhole, Fisheye, and Spherical Cameras

Hao Li, Huai Yu, Wen Yang +2

Line segment detection is essential for high-level tasks in computer vision and robotics. Currently, most stateof-the-art (SOTA) methods are dedicated to detecting straight line se…

cs.CV2020

Monocular Camera Localization in Prior LiDAR Maps with 2D-3D Line Correspondences

Huai Yu, Weikun Zhen, Wen Yang +2

Light-weight camera localization in existing maps is essential for vision-based navigation. Currently, visual and visual-inertial odometry (VO\&VIO) techniques are well-developed f…