• Publications
  • Influence
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
  • C. Ledig, L. Theis, +6 authors W. Shi
  • Computer Science, Mathematics
  • IEEE Conference on Computer Vision and Pattern…
  • 15 September 2016
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 recoverExpand
  • 3,600
  • 491
Lossy Image Compression with Compressive Autoencoders
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 typesExpand
  • 339
  • 58
A note on the evaluation of generative models
Probabilistic generative models can be used for compression, denoising, inpainting, texture synthesis, semi-supervised learning, unsupervised feature learning, and other tasks. Given this wide rangeExpand
  • 593
  • 38
Amortised MAP Inference for Image Super-resolution
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 SRExpand
  • 274
  • 24
Deep Gaze I: Boosting Saliency Prediction with Feature Maps Trained on ImageNet
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 ofExpand
  • 245
  • 18
Generative Image Modeling Using Spatial LSTMs
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 successfulExpand
  • 152
  • 14
Fast Face-Swap Using Convolutional Neural Networks
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 this mapping, weExpand
  • 86
  • 11
HoloGAN: Unsupervised Learning of 3D Representations From Natural Images
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 to generate imagesExpand
  • 63
  • 10
Faster gaze prediction with dense networks and Fisher pruning
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, theseExpand
  • 67
  • 10
Benchmarking Spike Rate Inference in Population Calcium Imaging
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 aExpand
  • 106
  • 7