411 citations · 1.7k across the 27 of their papers we have counts for
28 papers
High-Fidelity Image Compression with Score-based Generative Models
Emiel Hoogeboom, Eirikur Agustsson, Fabian Mentzer +3
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. In this…
Adaptive Greedy Rejection Sampling
Gergely Flamich, Lucas Theis
We consider channel simulation protocols between two communicating parties, Alice and Bob. First, Alice receives a target distribution , unknown to Bob. Then, she employs a shar…
Lossy Compression with Gaussian Diffusion
Lucas Theis, Tim Salimans, Matthew D. Hoffman +1
We consider a novel lossy compression approach based on unconditional diffusion generative models, which we call DiffC. Unlike modern compression schemes which rely on transform co…
An Introduction to Neural Data Compression
Yibo Yang, Stephan Mandt, Lucas Theis
Neural compression is the application of neural networks and other machine learning methods to data compression. Recent advances in statistical machine learning have opened up new…
Optimal Compression of Locally Differentially Private Mechanisms
Abhin Shah, Wei-Ning Chen, Johannes Balle +2
Compressing the output of ε-locally differentially private (LDP) randomizers naively leads to suboptimal utility. In this work, we demonstrate the benefits of using schemes that jo…
Algorithms for the Communication of Samples
Lucas Theis, Noureldin Yosri
The efficient communication of noisy data has applications in several areas of machine learning, such as neural compression or differential privacy, and is also known as reverse ch…
A coding theorem for the rate-distortion-perception function
Lucas Theis, Aaron B. Wagner
The rate-distortion-perception function (RDPF; Blau and Michaeli, 2019) has emerged as a useful tool for thinking about realism and distortion of reconstructions in lossy compressi…
On the advantages of stochastic encoders
Lucas Theis, Eirikur Agustsson
Stochastic encoders have been used in rate-distortion theory and neural compression because they can be easier to handle. However, in performance comparisons with deterministic enc…
Universally Quantized Neural Compression
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. We demon…
Discriminative Topic Modeling with Logistic LDA
Iryna Korshunova, Hanchen Xiong, Mateusz Fedoryszak +1
Despite many years of research into latent Dirichlet allocation (LDA), applying LDA to collections of non-categorical items is still challenging. Yet many problems with much richer…
Addressing Delayed Feedback for Continuous Training with Neural Networks in CTR prediction
Sofia Ira Ktena, Alykhan Tejani, Lucas Theis +5
One of the challenges in display advertising is that the distribution of features and click through rate (CTR) can exhibit large shifts over time due to seasonality, changes to ad…
HoloGAN: Unsupervised learning of 3D representations from natural images
Thu Nguyen-Phuoc, Chuan Li, Lucas Theis +2
We propose a novel generative adversarial network (GAN) for the task of unsupervised learning of 3D representations from natural images. Most generative models rely on 2D kernels t…
Adaptive Paired-Comparison Method for Subjective Video Quality Assessment on Mobile Devices
Katherine Storrs, Sebastiaan Van Leuven, Steve Kojder +2
To effectively evaluate subjective visual quality in weakly-controlled environments, we propose an Adaptive Paired Comparison method based on particle filtering. As our approach re…
Faster gaze prediction with dense networks and Fisher pruning
Lucas Theis, Iryna Korshunova, Alykhan Tejani +1
Predicting human fixations from images has recently seen large improvements by leveraging deep representations which were pretrained for object recognition. However, as we show in…
Checkerboard artifact free sub-pixel convolution: A note on sub-pixel convolution, resize convolution and convolution resize
Andrew Aitken, Christian Ledig, Lucas Theis +3
The most prominent problem associated with the deconvolution layer is the presence of checkerboard artifacts in output images and dense labels. To combat this problem, smoothness c…
Lossy Image Compression with Compressive Autoencoders
Lucas Theis, Wenzhe Shi, Andrew Cunningham +1
We propose a new approach to the problem of optimizing autoencoders for lossy image compression. New media formats, changing hardware technology, as well as diverse requirements an…
Fast Face-swap Using Convolutional Neural Networks
Iryna Korshunova, Wenzhe Shi, Joni Dambre +1
We consider the problem of face swapping in images, where an input identity is transformed into a target identity while preserving pose, facial expression, and lighting. To perform…
Amortised MAP Inference for Image Super-resolution
Casper Kaae Sønderby, Jose Caballero, Lucas Theis +2
Image super-resolution (SR) is an underdetermined inverse problem, where a large number of plausible high-resolution images can explain the same downsampled image. Most current sin…
Is the deconvolution layer the same as a convolutional layer?
Wenzhe Shi, Jose Caballero, Lucas Theis +4
In this note, we want to focus on aspects related to two questions most people asked us at CVPR about the network we presented. Firstly, What is the relationship between our propos…
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
Christian Ledig, Lucas Theis, Ferenc Huszar +8
Despite the breakthroughs in accuracy and speed of single image super-resolution using faster and deeper convolutional neural networks, one central problem remains largely unsolved…
A note on the evaluation of generative models
Lucas Theis, Aäron van den Oord, Matthias Bethge
Probabilistic generative models can be used for compression, denoising, inpainting, texture synthesis, semi-supervised learning, unsupervised feature learning, and other tasks. Giv…
Generative Image Modeling Using Spatial LSTMs
Lucas Theis, Matthias Bethge
Modeling the distribution of natural images is challenging, partly because of strong statistical dependencies which can extend over hundreds of pixels. Recurrent neural networks ha…
A Generative Model of Natural Texture Surrogates
Niklas Ludtke, Debapriya Das, Lucas Theis +1
Natural images can be viewed as patchworks of different textures, where the local image statistics is roughly stationary within a small neighborhood but otherwise varies from regio…
A trust-region method for stochastic variational inference with applications to streaming data
Lucas Theis, Matthew D. Hoffman
Stochastic variational inference allows for fast posterior inference in complex Bayesian models. However, the algorithm is prone to local optima which can make the quality of the p…