Zobrazeno 1 - 10
of 53
pro vyhledávání: '"Damodaran, Bharath Bhushan"'
Positional encodings are employed to capture the high frequency information of the encoded signals in implicit neural representation (INR). In this paper, we propose a novel positional encoding method which improves the reconstruction quality of the
Externí odkaz:
http://arxiv.org/abs/2311.06059
Autor:
Balcilar, Muhammet, Damodaran, Bharath Bhushan, Naser, Karam, Galpin, Franck, Hellier, Pierre
End-to-end image/video codecs are getting competitive compared to traditional compression techniques that have been developed through decades of manual engineering efforts. These trainable codecs have many advantages over traditional techniques such
Externí odkaz:
http://arxiv.org/abs/2308.00725
Deep variational autoencoders for image and video compression have gained significant attraction in the recent years, due to their potential to offer competitive or better compression rates compared to the decades long traditional codecs such as AVC,
Externí odkaz:
http://arxiv.org/abs/2303.03028
During the last four years, we have witnessed the success of end-to-end trainable models for image compression. Compared to decades of incremental work, these machine learning (ML) techniques learn all the components of the compression technique, whi
Externí odkaz:
http://arxiv.org/abs/2210.06596
We propose in this paper a new paradigm for facial video compression. We leverage the generative capacity of GANs such as StyleGAN to represent and compress a video, including intra and inter compression. Each frame is inverted in the latent space of
Externí odkaz:
http://arxiv.org/abs/2207.04324
Autor:
Damodaran, Bharath Bhushan, Jolly, Emmanuel, Puy, Gilles, Gosselin, Philippe Henri, Thébault, Cédric, Ahn, Junghyun, Christensen, Tim, Ghezzo, Paul, Hellier, Pierre
Publikováno v:
European Conference on Visual Media Production (CVMP '21), 2021
We present FacialFilmroll, a solution for spatially and temporally consistent editing of faces in one or multiple shots. We build upon unwrap mosaic [Rav-Acha et al. 2008] by specializing it to faces. We leverage recent techniques to fit a 3D face mo
Externí odkaz:
http://arxiv.org/abs/2110.02124
Generative adversarial networks (GANs) have proven to be surprisingly efficient for image editing by inverting and manipulating the latent code corresponding to a natural image. This property emerges from the disentangled nature of the latent space.
Externí odkaz:
http://arxiv.org/abs/2107.04481
Autor:
Fatras, Kilian, Damodaran, Bharath Bhushan, Lobry, Sylvain, Flamary, Rémi, Tuia, Devis, Courty, Nicolas
Noisy labels often occur in vision datasets, especially when they are obtained from crowdsourcing or Web scraping. We propose a new regularization method, which enables learning robust classifiers in presence of noisy data. To achieve this goal, we p
Externí odkaz:
http://arxiv.org/abs/1904.03936
Publikováno v:
Computer Vision and Image Understanding, Volume 191, 2020, 102863, ISSN 1077-3142
Deep neural networks have established as a powerful tool for large scale supervised classification tasks. The state-of-the-art performances of deep neural networks are conditioned to the availability of large number of accurately labeled samples. In
Externí odkaz:
http://arxiv.org/abs/1810.01163
Publikováno v:
J. of Applied Remote Sensing, 14(3), 036507 (2020)
Dimensionality reduction is an important step in processing the hyperspectral images (HSI) to overcome the curse of dimensionality problem. Linear dimensionality reduction methods such as Independent component analysis (ICA) and Linear discriminant a
Externí odkaz:
http://arxiv.org/abs/1804.07347