no code implementations • 12 Jul 2023 • Issa Khalifeh, Luka Murn, Marta Mrak, Ebroul Izquierdo
This network reduces the memory burden by close to 50% and runs up to four times faster during inference time compared to existing transformer-based interpolation methods.
no code implementations • 13 May 2022 • Issa Khalifeh, Marc Gorriz Blanch, Ebroul Izquierdo, Marta Mrak
Despite all the benefits interpolation methods offer, many of these networks require a lot of parameters, with more parameters meaning a heavier computational burden.
no code implementations • 16 Mar 2022 • Woody Bayliss, Luka Murn, Ebroul Izquierdo, Qianni Zhang, Marta Mrak
In video coding, in-loop filters are applied on reconstructed video frames to enhance their perceptual quality, before storing the frames for output.
no code implementations • 23 Apr 2020 • Maria Santamaria, Saverio Blasi, Ebroul Izquierdo, Marta Mrak
With the increasing demand for video content at higher resolutions, it is evermore critical to find ways to limit the complexity of video encoding tasks in order to reduce costs, power consumption and environmental impact of video services.
1 code implementation • 13 Mar 2020 • Maria Santamaria, Ebroul Izquierdo, Saverio Blasi, Marta Mrak
As reference frames are essential for exploiting temporal redundancies, intra frames are usually assigned a larger portion of the available bits.
1 code implementation • 14 Dec 2018 • Farzad Toutounchi, Ebroul Izquierdo
In this paper, we present a novel deep learning-based approach for still image super-resolution, that unlike the mainstream models does not rely solely on the input low resolution image for high quality upsampling, and takes advantage of a set of artificially created auxiliary self-replicas of the input image that are incorporated in the neural network to create an enhanced and accurate upscaling scheme.
no code implementations • 26 Sep 2018 • Michalis Giannopoulos, Grigorios Tsagkatakis, Saverio Blasi, Farzad Toutounchi, Athanasios Mouchtaris, Panagiotis Tsakalides, Marta Mrak, Ebroul Izquierdo
Moreover, transmission also introduces delays and other distortion types which affect the perceived quality.
1 code implementation • 28 Nov 2017 • Tomas Kliegr, Ebroul Izquierdo
A prediscretisation of numerical attributes which is required by some rule learning algorithms is a source of inefficiencies.
no code implementations • 4 Oct 2017 • Dongyu Zhang, Liang Lin, Tianshui Chen, Xian Wu, Wenwei Tan, Ebroul Izquierdo
Sketch portrait generation benefits a wide range of applications such as digital entertainment and law enforcement.
no code implementations • 28 Jul 2017 • Ziliang Chen, Keze Wang, Xiao Wang, Pai Peng, Ebroul Izquierdo, Liang Lin
Aiming at improving performance of visual classification in a cost-effective manner, this paper proposes an incremental semi-supervised learning paradigm called Deep Co-Space (DCS).
no code implementations • 6 Jul 2016 • Le Dong, Ling He, Gaipeng Kong, Qianni Zhang, Xiaochun Cao, Ebroul Izquierdo
In this paper, we propose a compact network called CUNet (compact unsupervised network) to counter the image classification challenge.
no code implementations • 18 Mar 2016 • Salehe Erfanian Ebadi, Valia Guerra Ones, Ebroul Izquierdo
This article addresses a few critical issues including: embedding global motion parameters in the matrix decomposition model, i. e., estimation of global motion parameters simultaneously with the foreground/background separation task, considering matrix block-sparsity rather than generic matrix sparsity as natural feature in video processing applications, attenuating background ghosting effects when foreground is subtracted, and more critically providing an extremely efficient algorithm to solve the low-rank/sparse matrix decomposition task.
no code implementations • 8 Jun 2015 • Craig Henderson, Ebroul Izquierdo
In this position paper, we consider the state of computer vision research with respect to invariance to the horizontal orientation of an image -- what we term reflection invariance.