Skip to search formSkip to main contentSkip to account menu
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
TLDR
SRGAN, a generative adversarial network (GAN) for image super-resolution (SR), is presented, to its knowledge, the first framework capable of inferring photo-realistic natural images for 4x upscaling factors and a perceptual loss function which consists of an adversarial loss and a content loss.
View on IEEE
Lossy Image Compression with Compressive Autoencoders
TLDR
It is shown that minimal changes to the loss are sufficient to train deep autoencoders competitive with JPEG 2000 and outperforming recently proposed approaches based on RNNs, and furthermore computationally efficient thanks to a sub-pixel architecture, which makes it suitable for high-resolution images.
View PDF on arXiv
A note on the evaluation of generative models
TLDR
This article reviews mostly known but often underappreciated properties relating to the evaluation and interpretation of generative models with a focus on image models and shows that three of the currently most commonly used criteria---average log-likelihood, Parzen window estimates, and visual fidelity of samples---are largely independent of each other when the data is high-dimensional.
View PDF on arXiv
HoloGAN: Unsupervised Learning of 3D Representations From Natural Images
TLDR
HoloGAN is the first generative model that learns 3D representations from natural images in an entirely unsupervised manner and is shown to be able to generate images with similar or higher visual quality than other generative models.
View on IEEE
Amortised MAP Inference for Image Super-resolution
TLDR
A novel neural network architecture is introduced that performs a projection to the affine subspace of valid SR solutions ensuring that the high resolution output of the network is always consistent with the low resolution input, and it is shown that the GAN based approach performs best on real image data.
View PDF on arXiv
Deep Gaze I: Boosting Saliency Prediction with Feature Maps Trained on ImageNet
TLDR
This work presents a novel way of reusing existing neural networks that have been pretrained on the task of object recognition in models of fixation prediction that significantly outperforms all state-of-the-art models on the MIT Saliency Benchmark.
View PDF on arXiv
Fast Face-Swap Using Convolutional Neural Networks
TLDR
A new loss function is devised that enables the network to produce highly photorealistic results by making face swap work in real-time with no input from the user.
View on IEEE
Generative Image Modeling Using Spatial LSTMs
TLDR
This work introduces a recurrent image model based on multidimensional long short-term memory units which is particularly suited for image modeling due to their spatial structure and outperforms the state of the art in quantitative comparisons on several image datasets and produces promising results when used for texture synthesis and inpainting.
View PDF on arXiv
Faster gaze prediction with dense networks and Fisher pruning
TLDR
Through a combination of knowledge distillation and Fisher pruning, this paper obtains much more runtime-efficient architectures for saliency prediction, achieving a 10x speedup for the same AUC performance as a state of the art network on the CAT2000 dataset.
View PDF on arXiv
Benchmarking Spike Rate Inference in Population Calcium Imaging
View on Elsevier
...
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy, Terms of Service, and Dataset License