Filter Results:
- Full text PDF available (25)
Publication Year
2011
2018
- This year (5)
- Last 5 years (26)
- Last 10 years (31)
Publication Type
Co-author
Journals and Conferences
Learn More
- Christian Ledig, Lucas Theis, +8 authors Wenzhe Shi
- 2017 IEEE Conference on Computer Vision and…
- 2017
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: how do we recover… (More)
- Lucas Theis, Aäron van den Oord, Matthias Bethge
- ArXiv
- 2015
Probabilistic generative models can be used for compression, denoising, inpainting, texture synthesis, semi-supervised learning, unsupervised feature learning, and other tasks. Given this wide range… (More)
- Matthias Kümmerer, Lucas Theis, Matthias Bethge
- ArXiv
- 2014
Recent results suggest that state-of-the-art saliency models perform far from optimal in predicting fixations. This lack in performance has been attributed to an inability to model the influence of… (More)
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 single image SR… (More)
- Lucas Theis, Wenzhe Shi, Andrew Cunningham, Ferenc Huszár
- ArXiv
- 2017
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 and content types… (More)
- Lucas Theis, Matthias Bethge
- NIPS
- 2015
Modeling the distribution of natural images is challenging, partly because of strong statistical dependencies which can extend over hundreds of pixels. Recurrent neural networks have been successful… (More)
- Lucas Theis, Philipp Berens, +6 authors Matthias Bethge
- Neuron
- 2016
A fundamental challenge in calcium imaging has been to infer spike rates of neurons from the measured noisy fluorescence traces. We systematically evaluate different spike inference algorithms on a… (More)
- Lucas Theis, Reshad Hosseini, Matthias Bethge
- PloS one
- 2012
We present a probabilistic model for natural images that is based on mixtures of Gaussian scale mixtures and a simple multiscale representation. We show that it is able to generate images with… (More)
- Lucas Theis, Iryna Korshunova, Alykhan Tejani, Ferenc Huszár
- ArXiv
- 2018
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 this paper, these… (More)
- Lucas Theis, Sebastian Gerwinn, Fabian H. Sinz, Matthias Bethge
- Journal of Machine Learning Research
- 2011
Statistical models of natural images provide an important t ool for researchers in the fields of machine learning and computational neuroscience. The canoni cal measure to quantitatively assess and… (More)