no code implementations • 3 Feb 2024 • Alina Ciocarlan, Sylvie Le Hégarat-Mascle, Sidonie Lefebvre, Arnaud Woiselle, Clara Barbanson
Traditional object detection methods such as YOLO struggle to detect tiny objects compared to segmentation neural networks, resulting in weaker performance when detecting small targets.
1 code implementation • 24 Jun 2023 • Benjamin Naoto Chiche, Julien N. Girard, Joana Frontera-Pons, Arnaud Woiselle, Jean-Luc Starck
Finally, based on the test data, we evaluate the source profile reconstruction performance of the proposed methods and classical image deconvolution algorithm CLEAN applied frame-by-frame.
no code implementations • 2 Mar 2023 • Alina Ciocarlan, Sylvie Le Hegarat-Mascle, Sidonie Lefebvre, Arnaud Woiselle
The detection of small objects is a challenging task in computer vision.
1 code implementation • CVPR 2022 • Benjamin Naoto Chiche, Arnaud Woiselle, Joana Frontera-Pons, Jean-Luc Starck
Finally, we introduce a new framework of recurrent VSR networks that is both stable and competitive, based on Lipschitz stability theory.
no code implementations • 23 Feb 2021 • Benjamin Naoto Chiche, Arnaud Woiselle, Joana Frontera-Pons, Jean-Luc Starck
Yet, they fail to incorporate some knowledge about the image formation model, which limits their flexibility.