Zobrazeno 1 - 10
of 24
pro vyhledávání: '"Erickson R"'
We introduce a lightweight and accurate architecture for resource-efficient visual correspondence. Our method, dubbed XFeat (Accelerated Features), revisits fundamental design choices in convolutional neural networks for detecting, extracting, and ma
Externí odkaz:
http://arxiv.org/abs/2404.19174
Autor:
Cadar, Felipe, Melo, Welerson, Kanagasabapathi, Vaishnavi, Potje, Guilherme, Martins, Renato, Nascimento, Erickson R.
Publikováno v:
Pattern Recognition Letters 2023
We propose a novel learned keypoint detection method to increase the number of correct matches for the task of non-rigid image correspondence. By leveraging true correspondences acquired by matching annotated image pairs with a specified descriptor e
Externí odkaz:
http://arxiv.org/abs/2309.00434
Local feature extraction is a standard approach in computer vision for tackling important tasks such as image matching and retrieval. The core assumption of most methods is that images undergo affine transformations, disregarding more complicated eff
Externí odkaz:
http://arxiv.org/abs/2304.00583
We present a novel learned keypoint detection method designed to maximize the number of correct matches for the task of non-rigid image correspondence. Our training framework uses true correspondences, obtained by matching annotated image pairs with
Externí odkaz:
http://arxiv.org/abs/2212.09589
Autor:
Kerim, Abdulrahman, Chamone, Felipe, Ramos, Washington, Marcolino, Leandro Soriano, Nascimento, Erickson R., Jiang, Richard
Recent semantic segmentation models perform well under standard weather conditions and sufficient illumination but struggle with adverse weather conditions and nighttime. Collecting and annotating training data under these conditions is expensive, ti
Externí odkaz:
http://arxiv.org/abs/2210.05626
Autor:
Kerim, Abdulrahman, Ramos, Washington L. S., Marcolino, Leandro Soriano, Nascimento, Erickson R., Jiang, Richard
Video stabilization plays a central role to improve videos quality. However, despite the substantial progress made by these methods, they were, mainly, tested under standard weather and lighting conditions, and may perform poorly under adverse condit
Externí odkaz:
http://arxiv.org/abs/2208.12763
Autor:
Ramos, Washington, Silva, Michel, Araujo, Edson, Moura, Victor, Oliveira, Keller, Marcolino, Leandro Soriano, Nascimento, Erickson R.
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. Despite the remarkable progress that summarization methods have made, mos
Externí odkaz:
http://arxiv.org/abs/2203.15778
Most of the existing handcrafted and learning-based local descriptors are still at best approximately invariant to affine image transformations, often disregarding deformable surfaces. In this paper, we take one step further by proposing a new approa
Externí odkaz:
http://arxiv.org/abs/2203.12016
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. In this paper, we present a new approach to compute features from
Externí odkaz:
http://arxiv.org/abs/2111.10617
Autor:
Gomes, Thiago L., Coutinho, Thiago M., Azevedo, Rafael, Martins, Renato, Nascimento, Erickson R.
This paper proposes a new end-to-end neural rendering architecture to transfer appearance and reenact human actors. Our method leverages a carefully designed graph convolutional network (GCN) to model the human body manifold structure, jointly with d
Externí odkaz:
http://arxiv.org/abs/2110.11746