no code implementations • 7 Feb 2024 • Natasha Butt, Blazej Manczak, Auke Wiggers, Corrado Rainone, David Zhang, Michaël Defferrard, Taco Cohen
Our method iterates between 1) program sampling and hindsight relabeling, and 2) learning from prioritized experience replay.
no code implementations • 2 Oct 2023 • Ties van Rozendaal, Tushar Singhal, Hoang Le, Guillaume Sautiere, Amir Said, Krishna Buska, Anjuman Raha, Dimitris Kalatzis, Hitarth Mehta, Frank Mayer, Liang Zhang, Markus Nagel, Auke Wiggers
This work presents the first neural video codec that decodes 1080p YUV420 video in real time on a mobile device.
no code implementations • 13 Jan 2023 • Noor Fathima Ghouse, Jens Petersen, Auke Wiggers, Tianlin Xu, Guillaume Sautière
Diffusion probabilistic models have recently achieved remarkable success in generating high quality image and video data.
no code implementations • 8 Aug 2022 • Reza Pourreza, Hoang Le, Amir Said, Guillaume Sautiere, Auke Wiggers
In video compression, coding efficiency is improved by reusing pixels from previously decoded frames via motion and residual compensation.
no code implementations • 18 Jul 2022 • Hoang Le, Liang Zhang, Amir Said, Guillaume Sautiere, Yang Yang, Pranav Shrestha, Fei Yin, Reza Pourreza, Auke Wiggers
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.
no code implementations • 19 Nov 2021 • Ties van Rozendaal, Johann Brehmer, Yunfan Zhang, Reza Pourreza, Auke Wiggers, Taco S. Cohen
We introduce a video compression algorithm based on instance-adaptive learning.
no code implementations • 11 Dec 2020 • Dana Kianfar, Auke Wiggers, Amir Said, Reza Pourreza, Taco Cohen
We train two classes of neural networks, a fully-convolutional network and an auto-regressive network, and evaluate each as a post-quantization step designed to refine cheap quantization schemes such as scalar quantization (SQ).
no code implementations • ICML 2020 • Auke Wiggers, Emiel Hoogeboom
Autoregressive models (ARMs) currently hold state-of-the-art performance in likelihood-based modeling of image and audio data.
no code implementations • 26 Apr 2019 • Jakub M. Tomczak, Romain Lepert, Auke Wiggers
Optimizing the execution time of tensor program, e. g., a convolution, involves finding its optimal configuration.