1 code implementation • 30 Aug 2022 • Hongkai Chen, Zixin Luo, Lei Zhou, Yurun Tian, Mingmin Zhen, Tian Fang, David McKinnon, Yanghai Tsin, Long Quan
Generating robust and reliable correspondences across images is a fundamental task for a diversity of applications.
1 code implementation • CVPR 2022 • Axel Barroso-Laguna, Yurun Tian, Krystian Mikolajczyk
We formulate the scale estimation problem as a prediction of a probability distribution over scale factors.
no code implementations • 6 Oct 2021 • Ruijie Ren, Mohit Gurnani Rajesh, Jordi Sanchez-Riera, Fan Zhang, Yurun Tian, Antonio Agudo, Yiannis Demiris, Krystian Mikolajczyk, Francesc Moreno-Noguer
We show that training our network solely with synthetic data and the proposed DA yields results competitive with models trained on real data.
1 code implementation • NeurIPS 2020 • Yurun Tian, Axel Barroso-Laguna, Tony Ng, Vassileios Balntas, Krystian Mikolajczyk
Recent works show that local descriptor learning benefits from the use of L2 normalisation, however, an in-depth analysis of this effect lacks in the literature.
no code implementations • 27 May 2020 • Yurun Tian, Vassileios Balntas, Tony Ng, Axel Barroso-Laguna, Yiannis Demiris, Krystian Mikolajczyk
In this paper, we present a novel approach that exploits the information within the descriptor space to propose keypoint locations.
1 code implementation • ECCV 2020 • Tony Ng, Vassileios Balntas, Yurun Tian, Krystian Mikolajczyk
One is focused on second-order spatial information to increase the performance of image descriptors, both local and global.
2 code implementations • CVPR 2019 • Yurun Tian, Xin Yu, Bin Fan, Fuchao Wu, Huub Heijnen, Vassileios Balntas
Despite the fact that Second Order Similarity (SOS) has been used with significant success in tasks such as graph matching and clustering, it has not been exploited for learning local descriptors.
1 code implementation • CVPR 2017 • Yurun Tian, Bin Fan, Fuchao Wu
In this paper, we propose to learn high per- formance descriptor in Euclidean space via the Convolu- tional Neural Network (CNN).