no code implementations • 5 Mar 2021 • Maciej Besta, Zur Vonarburg-Shmaria, Yannick Schaffner, Leonardo Schwarz, Grzegorz Kwasniewski, Lukas Gianinazzi, Jakub Beranek, Kacper Janda, Tobias Holenstein, Sebastian Leisinger, Peter Tatkowski, Esref Ozdemir, Adrian Balla, Marcin Copik, Philipp Lindenberger, Pavel Kalvoda, Marek Konieczny, Onur Mutlu, Torsten Hoefler
We propose GraphMineSuite (GMS): the first benchmarking suite for graph mining that facilitates evaluating and constructing high-performance graph mining algorithms.
1 code implementation • ICCV 2021 • Philipp Lindenberger, Paul-Edouard Sarlin, Viktor Larsson, Marc Pollefeys
Finding local features that are repeatable across multiple views is a cornerstone of sparse 3D reconstruction.
2 code implementations • ICCV 2023 • Philipp Lindenberger, Paul-Edouard Sarlin, Marc Pollefeys
We introduce LightGlue, a deep neural network that learns to match local features across images.