1 code implementation • 22 Nov 2022 • Marco Cotogni, Fei Yang, Claudio Cusano, Andrew D. Bagdanov, Joost Van de Weijer
Secondly, we propose a new method of feature drift compensation that accommodates feature drift in the backbone when learning new tasks.
1 code implementation • 14 Jul 2022 • Marco Cotogni, Claudio Cusano
In this paper we present a path planning algorithm which provides a step-by-step explanation of the output produced by state of the art enhancement methods, overcoming black-box limitation.
1 code implementation • 1 Jul 2022 • Marco Cotogni, Claudio Cusano
In this paper we present a framework for the design and implementation of offset equivariant networks, that is, neural networks that preserve in their output uniform increments in the input.
1 code implementation • 25 May 2022 • Marco Cotogni, Claudio Cusano
Given as input a low-light image, TreEnhance produces as output its enhanced version together with the sequence of image editing operations used to obtain it.
Ranked #1 on Image Enhancement on MIT-Adobe FiveK
no code implementations • 5 Aug 2015 • Claudio Cusano, Paolo Napoletano, Raimondo Schettini
The recognition of color texture under varying lighting conditions is still an open issue.
no code implementations • 5 Aug 2015 • Simone Bianco, Claudio Cusano, Raimondo Schettini
In this paper we present a method for the estimation of the color of the illuminant in RAW images.
no code implementations • 29 May 2015 • Simone Bianco, Gianluigi Ciocca, Claudio Cusano
The strategy, that is called CURL from Co-trained Unsupervised Representation Learning, iteratively builds two classifiers on two different views of the data.
1 code implementation • 17 Apr 2015 • Simone Bianco, Claudio Cusano, Raimondo Schettini
In this work we describe a Convolutional Neural Network (CNN) to accurately predict the scene illumination.
no code implementations • 20 Oct 2014 • Claudio Cusano, Paolo Napoletano, Raimondo Schettini
Experimental results on publicly available datasets demonstrate the feasibility of the proposed approach.