activity
20182024
most citedPolarization-driven Semantic Segmentation via Efficient Attention-bridged Fusion

108 citations · 146 across the 6 of their papers we have counts for

collaborators
Showing cs.CVShow all

14 papers · 1 filter

cs.CV2022

CSFlow: Learning Optical Flow via Cross Strip Correlation for Autonomous Driving

Hao Shi, Yifan Zhou, Kailun Yang +2

Optical flow estimation is an essential task in self-driving systems, which helps autonomous vehicles perceive temporal continuity information of surrounding scenes. The calculatio…

cs.CV202113 cited

Panoramic Depth Estimation via Supervised and Unsupervised Learning in Indoor Scenes

Keyang Zhou, Kailun Yang, Kaiwei Wang

Depth estimation, as a necessary clue to convert 2D images into the 3D space, has been applied in many machine vision areas. However, to achieve an entire surrounding 360-degree ge…

cs.CV2021

Aerial-PASS: Panoramic Annular Scene Segmentation in Drone Videos

Lei Sun, Jia Wang, Kailun Yang +4

Aerial pixel-wise scene perception of the surrounding environment is an important task for UAVs (Unmanned Aerial Vehicles). Previous research works mainly adopt conventional pinhol…

cs.CV2020108 cited

Polarization-driven Semantic Segmentation via Efficient Attention-bridged Fusion

Kaite Xiang, Kailun Yang, Kaiwei Wang

Semantic Segmentation (SS) is promising for outdoor scene perception in safety-critical applications like autonomous vehicles, assisted navigation and so on. However, traditional S…

cs.CV2020

Universal Semantic Segmentation for Fisheye Urban Driving Images

Yaozu Ye, Kailun Yang, Kaite Xiang +2

Semantic segmentation is a critical method in the field of autonomous driving. When performing semantic image segmentation, a wider field of view (FoV) helps to obtain more informa…

cs.CV2019

OpenMPR: Recognize Places Using Multimodal Data for People with Visual Impairments

Ruiqi Cheng, Kaiwei Wang, Jian Bai +1

Place recognition plays a crucial role in navigational assistance, and is also a challenging issue of assistive technology. The place recognition is prone to erroneous localization…