Zobrazeno 1 - 10
of 23
pro vyhledávání: '"Laskar, Zakaria"'
Autor:
Efthymiadis, Nikos, Psomas, Bill, Laskar, Zakaria, Karantzalos, Konstantinos, Avrithis, Yannis, Chum, Ondřej, Tolias, Giorgos
This work addresses composed image retrieval in the context of domain conversion, where the content of a query image is retrieved in the domain specified by the query text. We show that a strong vision-language model provides sufficient descriptive p
Externí odkaz:
http://arxiv.org/abs/2412.03297
Camera relocalization relies on 3D models of the scene with a large memory footprint that is incompatible with the memory budget of several applications. One solution to reduce the scene memory size is map compression by removing certain 3D points an
Externí odkaz:
http://arxiv.org/abs/2407.15540
Deep active learning in the presence of outlier examples poses a realistic yet challenging scenario. Acquiring unlabeled data for annotation requires a delicate balance between avoiding outliers to conserve the annotation budget and prioritizing usef
Externí odkaz:
http://arxiv.org/abs/2307.03741
Autor:
Wang, Shuzhe, Laskar, Zakaria, Melekhov, Iaroslav, Li, Xiaotian, Zhao, Yi, Tolias, Giorgos, Kannala, Juho
Visual localization is critical to many applications in computer vision and robotics. To address single-image RGB localization, state-of-the-art feature-based methods match local descriptors between a query image and a pre-built 3D model. Recently, d
Externí odkaz:
http://arxiv.org/abs/2305.03595
Fully-supervised CNN-based approaches for learning local image descriptors have shown remarkable results in a wide range of geometric tasks. However, most of them require per-pixel ground-truth keypoint correspondence data which is difficult to acqui
Externí odkaz:
http://arxiv.org/abs/2110.04773
For several emerging technologies such as augmented reality, autonomous driving and robotics, visual localization is a critical component. Directly regressing camera pose/3D scene coordinates from the input image using deep neural networks has shown
Externí odkaz:
http://arxiv.org/abs/2108.09112
Autor:
Laskar, Zakaria, Kannala, Juho
Recent advances in deep learning has lead to rapid developments in the field of image retrieval. However, the best performing architectures incur significant computational cost. Recent approaches tackle this issue using knowledge distillation to tran
Externí odkaz:
http://arxiv.org/abs/2007.05299
This paper addresses the problem of determining dense pixel correspondences between two images and its application to geometric correspondence verification in image retrieval. The main contribution is a geometric correspondence verification approach
Externí odkaz:
http://arxiv.org/abs/1904.06882
Autor:
Laskar, Zakaria, Kannala, Juho
Convolutional neural networks (CNNs) have been successfully applied to solve the problem of correspondence estimation between semantically related images. Due to non-availability of large training datasets, existing methods resort to self-supervised
Externí odkaz:
http://arxiv.org/abs/1901.08339
In this paper we address the problem of establishing correspondences between different instances of the same object. The problem is posed as finding the geometric transformation that aligns a given image pair. We use a convolutional neural network (C
Externí odkaz:
http://arxiv.org/abs/1901.08341