no code implementations • 17 May 2022 • Sourbh Bhadane, Aaron B. Wagner, Johannes Ballé
Artificial Neural-Network-based (ANN-based) lossy compressors have recently obtained striking results on several sources.
1 code implementation • 7 Jan 2022 • Nicole Mitchell, Johannes Ballé, Zachary Charles, Jakub Konečný
A significant bottleneck in federated learning (FL) is the network communication cost of sending model updates from client devices to the central server.
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.
no code implementations • ICLR 2022 • Alexander Hepburn, Valero Laparra, Raul Santos-Rodriguez, Johannes Ballé, Jesús Malo
Since machine learning relies on the statistics of training data as well, the above connection has interesting implications when using perceptual distances (which mimic the behavior of the human visual system) as a loss function.
no code implementations • 26 Apr 2021 • Thomas Bird, Johannes Ballé, Saurabh Singh, Philip A. Chou
We unify these steps by directly compressing an implicit representation of the scene, a function that maps spatial coordinates to a radiance vector field, which can then be queried to render arbitrary viewpoints.
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.
no code implementations • NeurIPS 2020 • Sangnie Bhardwaj, Ian Fischer, Johannes Ballé, Troy Chinen
We show that PIM is competitive with supervised metrics on the recent and challenging BAPPS image quality assessment dataset and outperforms them in predicting the ranking of image compression methods in CLIC 2020.
no code implementations • 18 Dec 2019 • Nick Johnston, Elad Eban, Ariel Gordon, Johannes Ballé
Image compression using neural networks have reached or exceeded non-neural methods (such as JPEG, WebP, BPG).
no code implementations • ICLR 2020 • Deniz Oktay, Johannes Ballé, Saurabh Singh, Abhinav Shrivastava
We describe a simple and general neural network weight compression approach, in which the network parameters (weights and biases) are represented in a "latent" space, amounting to a reparameterization.
no code implementations • ICLR 2019 • Johannes Ballé, Nick Johnston, David Minnen
We consider the problem of using variational latent-variable models for data compression.
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.
13 code implementations • ICLR 2018 • Johannes Ballé, David Minnen, Saurabh Singh, Sung Jin Hwang, Nick Johnston
We describe an end-to-end trainable model for image compression based on variational autoencoders.
3 code implementations • 31 Jan 2018 • Johannes Ballé
We assess the performance of two techniques in the context of nonlinear transform coding with artificial neural networks, Sadam and GDN.
no code implementations • NeurIPS 2017 • Alexander Berardino, Johannes Ballé, Valero Laparra, Eero P. Simoncelli
We develop a method for comparing hierarchical image representations in terms of their ability to explain perceptual sensitivity in humans.
no code implementations • 23 Jan 2017 • Valero Laparra, Alex Berardino, Johannes Ballé, Eero P. Simoncelli
We develop a framework for rendering photographic images, taking into account display limitations, so as to optimize perceptual similarity between the rendered image and the original scene.
13 code implementations • 5 Nov 2016 • Johannes Ballé, Valero Laparra, Eero P. Simoncelli
We describe an image compression method, consisting of a nonlinear analysis transformation, a uniform quantizer, and a nonlinear synthesis transformation.
no code implementations • 18 Jul 2016 • Johannes Ballé, Valero Laparra, Eero P. Simoncelli
We introduce a general framework for end-to-end optimization of the rate--distortion performance of nonlinear transform codes assuming scalar quantization.
1 code implementation • 19 Nov 2015 • Johannes Ballé, Valero Laparra, Eero P. Simoncelli
The data are linearly transformed, and each component is then normalized by a pooled activity measure, computed by exponentiating a weighted sum of rectified and exponentiated components and a constant.
no code implementations • 6 Jul 2015 • Neil C. Rabinowitz, Robbe L. T. Goris, Johannes Ballé, Eero P. Simoncelli
Neural responses are highly variable, and some portion of this variability arises from fluctuations in modulatory factors that alter their gain, such as adaptation, attention, arousal, expected or actual reward, emotion, and local metabolic resource availability.
no code implementations • 20 Dec 2014 • Olivier J. Hénaff, Johannes Ballé, Neil C. Rabinowitz, Eero P. Simoncelli
We develop a new statistical model for photographic images, in which the local responses of a bank of linear filters are described as jointly Gaussian, with zero mean and a covariance that varies slowly over spatial position.