1 code implementation • 23 Aug 2022 • Shu Tang, Yang Wu, Hongxing Qin, Xianzhong Xie, Shuli Yang, Jing Wang
Most existing deep-learning-based single image dynamic scene blind deblurring (SIDSBD) methods usually design deep networks to directly remove the spatially-variant motion blurs from one inputted motion blurred image, without blur kernels estimation.
no code implementations • 11 Nov 2017 • Xiangyu Zhu, Yingying Jiang, Shuli Yang, Xiaobing Wang, Wei Li, Pei Fu, Hua Wang, Zhenbo Luo
Scene text detection is a challenging problem in computer vision.
1 code implementation • 29 Jun 2017 • Yingying Jiang, Xiangyu Zhu, Xiaobing Wang, Shuli Yang, Wei Li, Hua Wang, Pei Fu, Zhenbo Luo
In this paper, we propose a novel method called Rotational Region CNN (R2CNN) for detecting arbitrary-oriented texts in natural scene images.