Search Results for author: Eirikur Agustsson

Found 22 papers, 7 papers with code

VCT: A Video Compression Transformer

no code implementations15 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.

motion prediction Video Compression

Neural Video Compression using GANs for Detail Synthesis and Propagation

no code implementations26 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.

Video Compression

On the advantages of stochastic encoders

no code implementations ICLR Workshop Neural_Compression 2021 Lucas Theis, Eirikur Agustsson

Stochastic encoders have been used in rate-distortion theory and neural compression because they can be easier to handle.

Universally Quantized Neural Compression

no code implementations NeurIPS 2020 Eirikur Agustsson, Lucas Theis

A popular approach to learning encoders for lossy compression is to use additive uniform noise during training as a differentiable approximation to test-time quantization.

Quantization

High-Fidelity Generative Image Compression

3 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.

Image Compression

Interactive Full Image Segmentation by Considering All Regions Jointly

no code implementations CVPR 2019 Eirikur Agustsson, Jasper R. R. Uijlings, Vittorio Ferrari

We propose an interactive, scribble-based annotation framework which operates on the whole image to produce segmentations for all regions.

Interactive Segmentation Semantic Segmentation

Practical Full Resolution Learned Lossless Image Compression

3 code implementations CVPR 2019 Fabian Mentzer, Eirikur Agustsson, Michael Tschannen, Radu Timofte, Luc van Gool

We propose the first practical learned lossless image compression system, L3C, and show that it outperforms the popular engineered codecs, PNG, WebP and JPEG 2000.

Image Compression

Towards Image Understanding from Deep Compression without Decoding

1 code implementation ICLR 2018 Robert Torfason, Fabian Mentzer, Eirikur Agustsson, Michael Tschannen, Radu Timofte, Luc van Gool

Motivated by recent work on deep neural network (DNN)-based image compression methods showing potential improvements in image quality, savings in storage, and bandwidth reduction, we propose to perform image understanding tasks such as classification and segmentation directly on the compressed representations produced by these compression methods.

Classification General Classification +1

Conditional Probability Models for Deep Image Compression

1 code implementation CVPR 2018 Fabian Mentzer, Eirikur Agustsson, Michael Tschannen, Radu Timofte, Luc van Gool

During training, the auto-encoder makes use of the context model to estimate the entropy of its representation, and the context model is concurrently updated to learn the dependencies between the symbols in the latent representation.

Image Compression MS-SSIM +3

ComboGAN: Unrestrained Scalability for Image Domain Translation

1 code implementation19 Dec 2017 Asha Anoosheh, Eirikur Agustsson, Radu Timofte, Luc Van Gool

This year alone has seen unprecedented leaps in the area of learning-based image translation, namely CycleGAN, by Zhu et al.

Image-to-Image Translation Translation

Logo Synthesis and Manipulation with Clustered Generative Adversarial Networks

no code implementations CVPR 2018 Alexander Sage, Eirikur Agustsson, Radu Timofte, Luc van Gool

We propose the use of synthetic labels obtained through clustering to disentangle and stabilize GAN training.

Optimal transport maps for distribution preserving operations on latent spaces of Generative Models

no code implementations ICLR 2018 Eirikur Agustsson, Alexander Sage, Radu Timofte, Luc van Gool

Generative models such as Variational Auto Encoders (VAEs) and Generative Adversarial Networks (GANs) are typically trained for a fixed prior distribution in the latent space, such as uniform or Gaussian.

Anchored Regression Networks Applied to Age Estimation and Super Resolution

no code implementations ICCV 2017 Eirikur Agustsson, Radu Timofte, Luc van Gool

We propose the Anchored Regression Network (ARN), a nonlinear regression network which can be seamlessly integrated into various networks or can be used stand-alone when the features have already been fixed.

Age Estimation Image Super-Resolution

WebVision Database: Visual Learning and Understanding from Web Data

no code implementations9 Aug 2017 Wen Li, Li-Min Wang, Wei Li, Eirikur Agustsson, Luc van Gool

Our new WebVision database and relevant studies in this work would benefit the advance of learning state-of-the-art visual models with minimum supervision based on web data.

Domain Adaptation

WebVision Challenge: Visual Learning and Understanding With Web Data

no code implementations16 May 2017 Wen Li, Li-Min Wang, Wei Li, Eirikur Agustsson, Jesse Berent, Abhinav Gupta, Rahul Sukthankar, Luc van Gool

The 2017 WebVision challenge consists of two tracks, the image classification task on WebVision test set, and the transfer learning task on PASCAL VOC 2012 dataset.

Image Classification Transfer Learning

k2-means for fast and accurate large scale clustering

no code implementations30 May 2016 Eirikur Agustsson, Radu Timofte, Luc van Gool

k^2-means builds upon the standard k-means (Lloyd's algorithm) and combines a new strategy to accelerate the convergence with a new low time complexity divisive initialization.

Neighborhood Selection for Thresholding-based Subspace Clustering

no code implementations13 Mar 2014 Reinhard Heckel, Eirikur Agustsson, Helmut Bölcskei

Subspace clustering refers to the problem of clustering high-dimensional data points into a union of low-dimensional linear subspaces, where the number of subspaces, their dimensions and orientations are all unknown.

Cannot find the paper you are looking for? You can Submit a new open access paper.