M
Mircea Cimpoi
Researcher at Czech Technical University in Prague
Publications - 10
Citations - 2532
Mircea Cimpoi is an academic researcher from Czech Technical University in Prague. The author has contributed to research in topics: Texture (geology) & Convolutional neural network. The author has an hindex of 9, co-authored 10 publications receiving 1674 citations. Previous affiliations of Mircea Cimpoi include Microsoft & University of Oxford.
Papers
More filters
Proceedings ArticleDOI
Describing Textures in the Wild
TL;DR: This work identifies a vocabulary of forty-seven texture terms and uses them to describe a large dataset of patterns collected "in the wild", and shows that they both outperform specialized texture descriptors not only on this problem, but also in established material recognition datasets.
Posted Content
Deep filter banks for texture recognition, description, and segmentation
TL;DR: In this article, a human-interpretable vocabulary of texture attributes is proposed to describe common texture patterns, complemented by a new describable texture dataset for benchmarking, and the problem of recognizing materials and texture attributes in realistic imaging conditions is addressed.
Journal ArticleDOI
Deep Filter Banks for Texture Recognition, Description, and Segmentation
TL;DR: The authors proposed a human-interpretable vocabulary of texture attributes to describe common texture patterns, complemented by a new describable texture dataset for benchmarking, and showed that these have excellent efficiency and generalization properties if the convolutional layers of a deep model are used as filter banks.
Proceedings Article
Neighbourhood Consensus Networks
TL;DR: An end-to-end trainable convolutional neural network architecture that identifies sets of spatially consistent matches by analyzing neighbourhood consensus patterns in the 4D space of all possible correspondences between a pair of images without the need for a global geometric model is developed.
Posted Content
Neighbourhood Consensus Networks
TL;DR: In this article, an end-to-end trainable convolutional neural network architecture is proposed to identify sets of spatially consistent matches by analyzing neighbourhood consensus patterns in the 4D space of all possible correspondences between a pair of images without the need for a global geometric model.