D
David Minnen
Researcher at Google
Publications - 54
Citations - 6004
David Minnen is an academic researcher from Google. The author has contributed to research in topics: Image compression & Artificial neural network. The author has an hindex of 25, co-authored 52 publications receiving 4205 citations. Previous affiliations of David Minnen include Georgia Institute of Technology College of Computing & Georgia Institute of Technology.
Papers
More filters
Proceedings Article
Variational image compression with a scale hyperprior
TL;DR: In this paper, an end-to-end trainable model for image compression based on variational autoencoders is proposed, which incorporates a hyperprior to effectively capture spatial dependencies in the latent representation.
Proceedings ArticleDOI
Full Resolution Image Compression with Recurrent Neural Networks
George Toderici,Damien Vincent,Nick Johnston,Sung Jin Hwang,David Minnen,Joel Shor,Michele Covell +6 more
TL;DR: 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.
Posted Content
Variable Rate Image Compression with Recurrent Neural Networks
George Toderici,Sean M. O'Malley,Sung Jin Hwang,Damien Vincent,David Minnen,Shumeet Baluja,Michele Covell,Rahul Sukthankar +7 more
TL;DR: A general framework for variable-rate image compression and a novel architecture based on convolutional and deconvolutional LSTM recurrent networks are proposed, which provide better visual quality than (headerless) JPEG, JPEG2000 and WebP, with a storage size reduced by 10% or more.
Posted Content
Full Resolution Image Compression with Recurrent Neural Networks
George Toderici,Damien Vincent,Nick Johnston,Sung Jin Hwang,David Minnen,Joel Shor,Michele Covell +6 more
TL;DR: In this paper, a set of full-resolution lossy image compression methods based on neural networks is presented, which can provide variable compression rates during deployment without requiring retraining of the network: each network need only be trained once.
Posted Content
Joint Autoregressive and Hierarchical Priors for Learned Image Compression
TL;DR: It is found that in terms of compression performance, autoregressive and hierarchical priors are complementary and can be combined to exploit the probabilistic structure in the latents better than all previous learned models.