2 code implementations • CVPR 2018 • Filip Radenović, Ahmet Iscen, Giorgos Tolias, Yannis Avrithis, Ondřej Chum
In particular, annotation errors, the size of the dataset, and the level of challenge are addressed: new annotation for both datasets is created with an extra attention to the reliability of the ground truth.
3 code implementations • 27 Nov 2018 • Arun Mukundan, Giorgos Tolias, Andrei Bursuc, Hervé Jégou, Ondřej Chum
We propose a multiple-kernel local-patch descriptor based on efficient match kernels from pixel gradients.
13 code implementations • 3 Nov 2017 • Filip Radenović, Giorgos Tolias, Ondřej Chum
We show that both hard-positive and hard-negative examples, selected by exploiting the geometry and the camera positions available from the 3D models, enhance the performance of particular-object retrieval.
Ranked #9 on Image Retrieval on RParis (Medium)
5 code implementations • 8 Apr 2016 • Filip Radenović, Giorgos Tolias, Ondřej Chum
Convolutional Neural Networks (CNNs) achieve state-of-the-art performance in many computer vision tasks.
Ranked #5 on Image Retrieval on Par6k
1 code implementation • 17 Jun 2021 • Matthijs Douze, Giorgos Tolias, Ed Pizzi, Zoë Papakipos, Lowik Chanussot, Filip Radenovic, Tomas Jenicek, Maxim Maximov, Laura Leal-Taixé, Ismail Elezi, Ondřej Chum, Cristian Canton Ferrer
This benchmark is used for the Image Similarity Challenge at NeurIPS'21 (ISC2021).
Ranked #1 on Image Similarity Detection on DISC21 dev
2 code implementations • ECCV 2018 • Filip Radenović, Giorgos Tolias, Ondřej Chum
We cast shape matching as metric learning with convolutional networks.
Ranked #1 on Sketch-Based Image Retrieval on Chairs (using extra training data)
2 code implementations • ECCV 2020 • Giorgos Tolias, Tomas Jenicek, Ondřej Chum
At inference, the local descriptors are provided by the activations of internal components of the network.
Ranked #5 on Image Retrieval on ROxford (Medium)
1 code implementation • ICCV 2019 • Tomas Jenicek, Ondřej Chum
Image retrieval under varying illumination conditions, such as day and night images, is addressed by image preprocessing, both hand-crafted and learned.
Ranked #3 on Image Retrieval on 24/7 Tokyo
1 code implementation • ICCV 2019 • Giorgos Tolias, Filip Radenovic, Ondřej Chum
We show successful attacks to partially unknown systems, by designing various loss functions for the adversarial image construction.
1 code implementation • 25 Jul 2019 • James Pritts, Zuzana Kukelova, Viktor Larsson, Yaroslava Lochman, Ondřej Chum
The proposed solvers use the affine invariant that coplanar repeats have the same scale in rectified space.
1 code implementation • 4 Nov 2019 • James Pritts, Zuzana Kukelova, Viktor Larsson, Yaroslava Lochman, Ondřej Chum
This paper introduces minimal solvers that jointly solve for radial lens undistortion and affine-rectification using local features extracted from the image of coplanar translated and reflected scene texture, which is common in man-made environments.
1 code implementation • ICCV 2023 • Albert Mohwald, Tomas Jenicek, Ondřej Chum
We propose to train a GAN-based synthetic-image generator, translating available day-time image examples into night images.
Ranked #1 on Image Retrieval on 24/7 Tokyo
no code implementations • CVPR 2017 • Giorgos Tolias, Ondřej Chum
To demonstrate the advantages of the AFM method, we derive a short vector image representation that, due to asymmetric feature maps, supports efficient scale and translation invariant sketch-based image retrieval.
no code implementations • 8 Jul 2019 • Tomas Jenicek, Ondřej Chum
We address the discovery of composition transfer in artworks based on their visual content.
no code implementations • 9 Feb 2022 • Assia Benbihi, Cédric Pradalier, Ondřej Chum
Direct matching of local features is sensitive to significant changes in illumination.
no code implementations • ICCV 2023 • Nikolaos-Antonios Ypsilantis, KaiFeng Chen, Bingyi Cao, Mário Lipovský, Pelin Dogan-Schönberger, Grzegorz Makosa, Boris Bluntschli, Mojtaba Seyedhosseini, Ondřej Chum, André Araujo
In this work, we address the problem of universal image embedding, where a single universal model is trained and used in multiple domains.