Zobrazeno 1 - 10
of 13
pro vyhledávání: '"Sautiere, Guillaume"'
The rise of new video modalities like virtual reality or autonomous driving has increased the demand for efficient multi-view video compression methods, both in terms of rate-distortion (R-D) performance and in terms of delay and runtime. While most
Externí odkaz:
http://arxiv.org/abs/2403.17879
Autor:
Habibian, Amirhossein, Ghodrati, Amir, Fathima, Noor, Sautiere, Guillaume, Garrepalli, Risheek, Porikli, Fatih, Petersen, Jens
This work aims to improve the efficiency of text-to-image diffusion models. While diffusion models use computationally expensive UNet-based denoising operations in every generation step, we identify that not all operations are equally relevant for th
Externí odkaz:
http://arxiv.org/abs/2312.08128
Autor:
van Rozendaal, Ties, Singhal, Tushar, Le, Hoang, Sautiere, Guillaume, Said, Amir, Buska, Krishna, Raha, Anjuman, Kalatzis, Dimitris, Mehta, Hitarth, Mayer, Frank, Zhang, Liang, Nagel, Markus, Wiggers, Auke
Neural video codecs have recently become competitive with standard codecs such as HEVC in the low-delay setting. However, most neural codecs are large floating-point networks that use pixel-dense warping operations for temporal modeling, making them
Externí odkaz:
http://arxiv.org/abs/2310.01258
Diffusion probabilistic models have recently achieved remarkable success in generating high quality image and video data. In this work, we build on this class of generative models and introduce a method for lossy compression of high resolution images
Externí odkaz:
http://arxiv.org/abs/2301.05489
In video compression, coding efficiency is improved by reusing pixels from previously decoded frames via motion and residual compensation. We define two levels of hierarchical redundancy in video frames: 1) first-order: redundancy in pixel space, i.e
Externí odkaz:
http://arxiv.org/abs/2208.04303
Autor:
Le, Hoang, Zhang, Liang, Said, Amir, Sautiere, Guillaume, Yang, Yang, Shrestha, Pranav, Yin, Fei, Pourreza, Reza, Wiggers, Auke
Realizing the potential of neural video codecs on mobile devices is a big technological challenge due to the computational complexity of deep networks and the power-constrained mobile hardware. We demonstrate practical feasibility by leveraging Qualc
Externí odkaz:
http://arxiv.org/abs/2207.08338
Autor:
Perugachi-Diaz, Yura, Sautière, Guillaume, Abati, Davide, Yang, Yang, Habibian, Amirhossein, Cohen, Taco S
Humans do not perceive all parts of a scene with the same resolution, but rather focus on few regions of interest (ROIs). Traditional Object-Based codecs take advantage of this biological intuition, and are capable of non-uniform allocation of bits i
Externí odkaz:
http://arxiv.org/abs/2203.01978
When training end-to-end learned models for lossy compression, one has to balance the rate and distortion losses. This is typically done by manually setting a tradeoff parameter $\beta$, an approach called $\beta$-VAE. Using this approach it is diffi
Externí odkaz:
http://arxiv.org/abs/2005.04064
Recent advances in deep generative modeling have enabled efficient modeling of high dimensional data distributions and opened up a new horizon for solving data compression problems. Specifically, autoencoder based learned image or video compression s
Externí odkaz:
http://arxiv.org/abs/2004.04342
Publikováno v:
ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
In this work, we propose a new recurrent autoencoder architecture, termed Feedback Recurrent AutoEncoder (FRAE), for online compression of sequential data with temporal dependency. The recurrent structure of FRAE is designed to efficiently extract th
Externí odkaz:
http://arxiv.org/abs/1911.04018