no code implementations • 10 Nov 2023 • Bharath Bhushan Damodaran, Francois Schnitzler, Anne Lambert, Pierre Hellier
Positional encodings are employed to capture the high frequency information of the encoded signals in implicit neural representation (INR).
no code implementations • 1 Aug 2023 • Muhammet Balcilar, Bharath Bhushan Damodaran, Karam Naser, Franck Galpin, Pierre Hellier
End-to-end image/video codecs are getting competitive compared to traditional compression techniques that have been developed through decades of manual engineering efforts.
no code implementations • 10 Mar 2023 • Franck Galpin, Muhammet Balcilar, Frédéric Lefebvre, Fabien Racapé, Pierre Hellier
End-to-end image and video compression using auto-encoders (AE) offers new appealing perspectives in terms of rate-distortion gains and applications.
no code implementations • 6 Mar 2023 • Bharath Bhushan Damodaran, Muhammet Balcilar, Franck Galpin, Pierre Hellier
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, HEVC or VVC.
no code implementations • 12 Oct 2022 • Muhammet Balcilar, Bharath Bhushan Damodaran, Pierre Hellier
In this paper, we propose to evaluate the amortization gap for three state-of-the-art ML video compression methods.
no code implementations • 2 Sep 2022 • Muhammet Balcilar, Bharath Damodaran, Pierre Hellier
The decoder is also learned as a deep trainable network, and the reconstructed image measures the distortion.
no code implementations • 9 Jul 2022 • Mustafa Shukor, Bharath Bhushan Damodaran, Xu Yao, Pierre Hellier
We leverage the generative capacity of GANs such as StyleGAN to represent and compress a video, including intra and inter compression.
no code implementations • 29 Jun 2022 • Mustafa Shukor, Xu Yao, Bharath Bushan Damodaran, Pierre Hellier
Generative adversarial networks (GANs) have proven to be surprisingly efficient for image editing by inverting and manipulating the latent code corresponding to an input real image.
1 code implementation • 4 Feb 2022 • Xu Yao, Alasdair Newson, Yann Gousseau, Pierre Hellier
Additionally, we demonstrate that the proposed encoder is especially well-suited for inversion and editing on videos.
no code implementations • 5 Oct 2021 • Bharath Bhushan Damodaran, Emmanuel Jolly, Gilles Puy, Philippe Henri Gosselin, Cédric Thébault, Junghyun Ahn, Tim Christensen, Paul Ghezzo, Pierre Hellier
We present FacialFilmroll, a solution for spatially and temporally consistent editing of faces in one or multiple shots.
no code implementations • 29 Sep 2021 • Mustafa Shukor, Xu Yao, Bharath Bhushan Damodaran, Pierre Hellier
We leverage the generative capacity of GANs such as StyleGAN to represent and compress each video frame (intra compression), as well as the successive differences between frames (inter compression).
no code implementations • 9 Jul 2021 • Mustafa Shukor, Xu Yao, Bharath Bhushan Damodaran, Pierre Hellier
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.
1 code implementation • ICCV 2021 • Xu Yao, Alasdair Newson, Yann Gousseau, Pierre Hellier
Previous works that attempt to tackle this problem may suffer from the entanglement of facial attributes and the loss of the person's identity.
no code implementations • 2 Jul 2020 • Lucas Mourot, François Le Clerc, Cédric Thébault, Pierre Hellier
Human Pose Estimation is a low-level task useful forsurveillance, human action recognition, and scene understandingat large.
2 code implementations • 9 May 2020 • Xu Yao, Gilles Puy, Alasdair Newson, Yann Gousseau, Pierre Hellier
We present an encoder-decoder architecture for face age editing.
no code implementations • CVPR 2016 • Oriel Frigo, Neus Sabater, Julie Delon, Pierre Hellier
This paper presents a novel unsupervised method to transfer the style of an example image to a source image.