no code implementations • 26 May 2023 • Emiel Hoogeboom, Eirikur Agustsson, Fabian Mentzer, Luca Versari, George Toderici, Lucas Theis
Despite the tremendous success of diffusion generative models in text-to-image generation, replicating this success in the domain of image compression has proven difficult.
1 code implementation • CVPR 2023 • Eirikur Agustsson, David Minnen, George Toderici, Fabian Mentzer
By optimizing the rate-distortion-realism trade-off, generative compression approaches produce detailed, realistic images, even at low bit rates, instead of the blurry reconstructions produced by rate-distortion optimized models.
1 code implementation • 15 Jun 2022 • Fabian Mentzer, George Toderici, David Minnen, Sung-Jin Hwang, Sergi Caelles, Mario Lucic, Eirikur Agustsson
The resulting video compression transformer outperforms previous methods on standard video compression data sets.
1 code implementation • 17 Nov 2021 • Berivan Isik, Philip A. Chou, Sung Jin Hwang, Nick Johnston, George Toderici
We consider the attributes of a point cloud as samples of a vector-valued volumetric function at discrete positions.
no code implementations • 26 Jul 2021 • Fabian Mentzer, Eirikur Agustsson, Johannes Ballé, David Minnen, Nick Johnston, George Toderici
Our approach significantly outperforms previous neural and non-neural video compression methods in a user study, setting a new state-of-the-art in visual quality for neural methods.
1 code implementation • 23 Jul 2020 • Saurabh Singh, Sami Abu-El-Haija, Nick Johnston, Johannes Ballé, Abhinav Shrivastava, George Toderici
We propose a learned method that jointly optimizes for compressibility along with the task objective for learning the features.
4 code implementations • NeurIPS 2020 • Fabian Mentzer, George Toderici, Michael Tschannen, Eirikur Agustsson
We extensively study how to combine Generative Adversarial Networks and learned compression to obtain a state-of-the-art generative lossy compression system.
3 code implementations • NeurIPS 2018 • David Minnen, Johannes Ballé, George Toderici
While it is well known that autoregressive models come with a significant computational penalty, we find that in terms of compression performance, autoregressive and hierarchical priors are complementary and, together, exploit the probabilistic structure in the latents better than all previous learned models.
no code implementations • 1 Aug 2018 • Troy Chinen, Johannes Ballé, Chunhui Gu, Sung Jin Hwang, Sergey Ioffe, Nick Johnston, Thomas Leung, David Minnen, Sean O'Malley, Charles Rosenberg, George Toderici
We present a full reference, perceptual image metric based on VGG-16, an artificial neural network trained on object classification.
no code implementations • 31 May 2018 • David Minnen, George Toderici, Saurabh Singh, Sung Jin Hwang, Michele Covell
The leading approach for image compression with artificial neural networks (ANNs) is to learn a nonlinear transform and a fixed entropy model that are optimized for rate-distortion performance.
no code implementations • 7 Feb 2018 • David Minnen, George Toderici, Michele Covell, Troy Chinen, Nick Johnston, Joel Shor, Sung Jin Hwang, Damien Vincent, Saurabh Singh
Deep neural networks represent a powerful class of function approximators that can learn to compress and reconstruct images.
8 code implementations • CVPR 2018 • Chunhui Gu, Chen Sun, David A. Ross, Carl Vondrick, Caroline Pantofaru, Yeqing Li, Sudheendra Vijayanarasimhan, George Toderici, Susanna Ricco, Rahul Sukthankar, Cordelia Schmid, Jitendra Malik
The AVA dataset densely annotates 80 atomic visual actions in 430 15-minute video clips, where actions are localized in space and time, resulting in 1. 58M action labels with multiple labels per person occurring frequently.
Ranked #6 on Action Detection on UCF101-24
no code implementations • 18 May 2017 • Michele Covell, Nick Johnston, David Minnen, Sung Jin Hwang, Joel Shor, Saurabh Singh, Damien Vincent, George Toderici
Our methods introduce a multi-pass training method to combine the training goals of high-quality reconstructions in areas around stop-code masking as well as in highly-detailed areas.
no code implementations • CVPR 2018 • Nick Johnston, Damien Vincent, David Minnen, Michele Covell, Saurabh Singh, Troy Chinen, Sung Jin Hwang, Joel Shor, George Toderici
We propose a method for lossy image compression based on recurrent, convolutional neural networks that outperforms BPG (4:2:0 ), WebP, JPEG2000, and JPEG as measured by MS-SSIM.
6 code implementations • 27 Sep 2016 • Sami Abu-El-Haija, Nisarg Kothari, Joonseok Lee, Paul Natsev, George Toderici, Balakrishnan Varadarajan, Sudheendra Vijayanarasimhan
Despite the size of the dataset, some of our models train to convergence in less than a day on a single machine using TensorFlow.
Ranked #1 on Action Recognition In Videos on ActivityNet
7 code implementations • CVPR 2017 • George Toderici, Damien Vincent, Nick Johnston, Sung Jin Hwang, David Minnen, Joel Shor, Michele Covell
As far as we know, this is the first neural network architecture that is able to outperform JPEG at image compression across most bitrates on the rate-distortion curve on the Kodak dataset images, with and without the aid of entropy coding.
1 code implementation • 19 Nov 2015 • George Toderici, Sean M. O'Malley, Sung Jin Hwang, Damien Vincent, David Minnen, Shumeet Baluja, Michele Covell, Rahul Sukthankar
A large fraction of Internet traffic is now driven by requests from mobile devices with relatively small screens and often stringent bandwidth requirements.
no code implementations • 1 Jul 2015 • Greg Mori, Caroline Pantofaru, Nisarg Kothari, Thomas Leung, George Toderici, Alexander Toshev, Weilong Yang
We present a method for learning an embedding that places images of humans in similar poses nearby.
no code implementations • 22 May 2015 • Balakrishnan Varadarajan, George Toderici, Sudheendra Vijayanarasimhan, Apostol Natsev
We present two methods that build on this work, and scale it up to work with millions of videos and hundreds of thousands of classes while maintaining a low computational cost.
1 code implementation • CVPR 2015 • Joe Yue-Hei Ng, Matthew Hausknecht, Sudheendra Vijayanarasimhan, Oriol Vinyals, Rajat Monga, George Toderici
Convolutional neural networks (CNNs) have been extensively applied for image recognition problems giving state-of-the-art results on recognition, detection, segmentation and retrieval.
Ranked #5 on Action Recognition on Sports-1M
1 code implementation • 2014 IEEE Conference on Computer Vision and Pattern Recognition 2014 • Andrej Karpathy, George Toderici, Sanketh Shetty, Thomas Leung, Rahul Sukthankar, Li Fei-Fei
We further study the generalization performance of our best model by retraining the top layers on the UCF-101 Action Recognition dataset and observe significant performance improvements compared to the UCF-101 baseline model (63. 3% up from 43. 9%).
Ranked #9 on Action Recognition on Sports-1M