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 • 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.
1 code implementation • 11 Oct 2022 • Abdulrahman Kerim, Felipe Chamone, Washington Ramos, Leandro Soriano Marcolino, Erickson R. Nascimento, Richard Jiang
Recent semantic segmentation models perform well under standard weather conditions and sufficient illumination but struggle with adverse weather conditions and nighttime.
1 code implementation • 26 Aug 2022 • Abdulrahman Kerim, Washington L. S. Ramos, Leandro Soriano Marcolino, Erickson R. Nascimento, Richard Jiang
In this paper, we propose a synthetic-aware adverse weather robust algorithm for video stabilization that does not require real data and can be trained only on synthetic data.
1 code implementation • 29 Mar 2022 • Washington Ramos, Michel Silva, Edson Araujo, Victor Moura, Keller Oliveira, Leandro Soriano Marcolino, Erickson R. Nascimento
The growth of videos in our digital age and the users' limited time raise the demand for processing untrimmed videos to produce shorter versions conveying the same information.
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.
no code implementations • 22 Oct 2021 • Thiago L. Gomes, Thiago M. Coutinho, Rafael Azevedo, Renato Martins, Erickson R. Nascimento
It also infers texture appearance with a convolutional network in the texture domain, which is trained in an adversarial regime to reconstruct human texture from rendered images of actors in different poses.
no code implementations • 29 Mar 2021 • Thiago L. Gomes, Renato Martins, João Ferreira, Rafael Azevedo, Guilherme Torres, Erickson R. Nascimento
Transferring human motion and appearance between videos of human actors remains one of the key challenges in Computer Vision.
1 code implementation • 25 Nov 2020 • João P. Ferreira, Thiago M. Coutinho, Thiago L. Gomes, José F. Neto, Rafael Azevedo, Renato Martins, Erickson R. Nascimento
Our method uses an adversarial learning scheme conditioned on the input music audios to create natural motions preserving the key movements of different music styles.
1 code implementation • 13 Mar 2020 • Renato Martins, Dhiego Bersan, Mario F. M. Campos, Erickson R. Nascimento
The formulation is designed to identify and to disregard dynamic objects in order to obtain a medium-term invariant map representation.
no code implementations • 8 Jan 2020 • Thiago L. Gomes, Renato Martins, João Ferreira, Erickson R. Nascimento
Differently from recent appearance transferring methods, our approach takes into account body shape, appearance, and motion constraints.
no code implementations • 29 Dec 2019 • Washington L. S. Ramos, Michel M. Silva, Edson R. Araujo, Alan C. Neves, Erickson R. Nascimento
In this work, we present a new approach to automatically creating personalized fast-forward videos for FPVs.
no code implementations • ICCV 2019 • Erickson R. Nascimento, Guilherme Potje, Renato Martins, Felipe Cadar, Mario F. M. Campos, Ruzena Bajcsy
At the core of most three-dimensional alignment and tracking tasks resides the critical problem of point correspondence.
no code implementations • 12 Sep 2018 • Bruna Vieira Frade, Erickson R. Nascimento
The detection of fiducial points on faces has significantly been favored by the rapid progress in the field of machine learning, in particular in the convolution networks.
no code implementations • 12 Jun 2018 • Vinicius S. Furlan, Ruzena Bajcsy, Erickson R. Nascimento
The remarkable technological advance in well-equipped wearable devices is pushing an increasing production of long first-person videos.
no code implementations • CVPR 2018 • Michel Silva, Washington Ramos, João Ferreira, Felipe Chamone, Mario Campos, Erickson R. Nascimento
Thanks to the advances in the technology of low-cost digital cameras and the popularity of the self-recording culture, the amount of visual data on the Internet is going to the opposite side of the available time and patience of the users.
no code implementations • 24 Aug 2017 • Guilherme Nascimento, Camila Laranjeira, Vinicius Braz, Anisio Lacerda, Erickson R. Nascimento
In this paper, we present a robust method for scene recognition, which leverages Convolutional Neural Networks (CNNs) features and Sparse Coding setting by creating a new representation of indoor scenes.
no code implementations • 1 Apr 2017 • Manoel Horta Ribeiro, Bruno Teixeira, Antônio Otávio Fernandes, Wagner Meira Jr., Erickson R. Nascimento
We then use it to assign the latent values to the label values.