no code implementations • CVPR 2022 • Tony Ng, Hyo Jin Kim, Vincent Lee, Daniel DeTone, Tsun-Yi Yang, Tianwei Shen, Eddy Ilg, Vassileios Balntas, Krystian Mikolajczyk, Chris Sweeney
We let a feature encoding network and image reconstruction network compete with each other, such that the feature encoder tries to impede the image reconstruction with its generated descriptors, while the reconstructor tries to recover the input image from the descriptors.
no code implementations • 16 Aug 2021 • Tony Ng, Adrian Lopez-Rodriguez, Vassileios Balntas, Krystian Mikolajczyk
In this paper, we address the problem of camera pose estimation in outdoor and indoor scenarios.
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.
no code implementations • 20 Jan 2020 • Tsun-Yi Yang, Duy-Kien Nguyen, Huub Heijnen, Vassileios Balntas
In this paper, we explore how three related tasks, namely keypoint detection, description, and image retrieval can be jointly tackled using a single unified framework, which is trained without the need of training data with point to point correspondences.
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.
no code implementations • ECCV 2018 • Vassileios Balntas, Shuda Li, Victor Prisacariu
We propose a method of learning suitable convolutional representations for camera pose retrieval based on nearest neighbour matching and continuous metric learning-based feature descriptors.
no code implementations • ICCV 2017 • Vassileios Balntas, Andreas Doumanoglou, Caner Sahin, Juil Sock, Rigas Kouskouridas, Tae-Kyun Kim
In this paper we examine the effects of using object poses as guidance to learning robust features for 3D object pose estimation.
no code implementations • 1 Aug 2017 • Baris Gecer, Vassileios Balntas, Tae-Kyun Kim
In this work, we investigate several methods and strategies to learn deep embeddings for face recognition, using joint sample- and set-based optimization.
no code implementations • CVPR 2017 • Vassileios Balntas, Karel Lenc, Andrea Vedaldi, Krystian Mikolajczyk
In this paper, we propose a novel benchmark for evaluating local image descriptors.
no code implementations • 8 Jul 2016 • Andreas Doumanoglou, Vassileios Balntas, Rigas Kouskouridas, Tae-Kyun Kim
Furthermore, we argue that our pose-guided feature learning using our Siamese Regression Network generates more discriminative features that outperform the state of the art.
1 code implementation • 19 Jan 2016 • Vassileios Balntas, Edward Johns, Lilian Tang, Krystian Mikolajczyk
We address this problem and propose a CNN based descriptor with improved matching performance, significantly reduced training and execution time, as well as low dimensionality.
no code implementations • CVPR 2015 • Vassileios Balntas, Lilian Tang, Krystian Mikolajczyk
The patch adapted descriptors are then efficiently built online from a subset of tests which lead to lower intra class distances thus a more robust descriptor.