no code implementations • 30 Apr 2024 • Guilherme Potje, Felipe Cadar, Andre Araujo, Renato Martins, Erickson R. Nascimento
Besides, our model is designed to offer the choice of matching at the sparse or semi-dense levels, each of which may be more suitable for different downstream applications, such as visual navigation and augmented reality.
1 code implementation • 1 Sep 2023 • Felipe Cadar, Welerson Melo, Vaishnavi Kanagasabapathi, Guilherme Potje, Renato Martins, Erickson R. Nascimento
We propose a novel learned keypoint detection method to increase the number of correct matches for the task of non-rigid image correspondence.
1 code implementation • ICCV 2023 • Thomas Mensink, Jasper Uijlings, Lluis Castrejon, Arushi Goel, Felipe Cadar, Howard Zhou, Fei Sha, André Araujo, Vittorio Ferrari
Empirically, we show that our dataset poses a hard challenge for large vision+language models as they perform poorly on our dataset: PaLI [14] is state-of-the-art on OK-VQA [37], yet it only achieves 13. 0% accuracy on our dataset.
1 code implementation • CVPR 2023 • Guilherme Potje, Felipe Cadar, Andre Araujo, Renato Martins, Erickson R. Nascimento
Local feature extraction is a standard approach in computer vision for tackling important tasks such as image matching and retrieval.
1 code implementation • 13 Dec 2022 • Welerson Melo, Guilherme Potje, Felipe Cadar, Renato Martins, Erickson R. Nascimento
We present a novel learned keypoint detection method designed to maximize the number of correct matches for the task of non-rigid image correspondence.
no code implementations • 22 Mar 2022 • Guilherme Potje, Renato Martins, Felipe Cadar, Erickson R. Nascimento
Most of the existing handcrafted and learning-based local descriptors are still at best approximately invariant to affine image transformations, often disregarding deformable surfaces.
1 code implementation • NeurIPS 2021 • Guilherme Potje, Renato Martins, Felipe Cadar, Erickson R. Nascimento
Despite the advances in extracting local features achieved by handcrafted and learning-based descriptors, they are still limited by the lack of invariance to non-rigid transformations.