Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks

By Emily L. Denton, Soumith Chintala, Arthur Szlam, Rob Fergus. 2015

2,348 citations recorded by the source corpus.

In this paper we introduce a generative parametric model capable of producing high quality samples of natural images. Our approach uses a cascade of convolutional networks within a Laplacian pyramid framework to generate images in a coarse-to-fine fashion. At each level of the pyramid, a separate generative convnet model is trained using the Generative Adversarial Nets (GAN) approach [11]. Samples drawn from our model are of significantly higher quality than alternate approaches. In a quantitative assessment by human evaluators, our CIFAR10 samples were mistaken for real images around 40% of the time, compared to 10% for samples drawn from a GAN baseline model. We also show samples from models trained on the higher resolution images of the LSUN scene dataset.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Generative Models

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Generative Models

Citations in the corpus

Generating Sentences from a Continuous Space (2015, methodology): “Adversarial evaluation Drawing inspiration from adversarial training methods for generative models as well as non-parametric two-sample tests (Goodfellow et al., 2014; Li et al., 2015b; Denton et al., 2015; Gretton et al., 2012), we evaluate the imputed sentence completions by examining their distin”
Analyzing and Improving the Image Quality of StyleGAN (2019, methodology): “This design is similar to LAPGAN [6] without the per-resolution discriminators employed by Denton et al.”
Learning Energy-Based Spatial-Temporal Generative ConvNets for Dynamic Patterns (2019, methodology): “In terms of synthesis, various approaches based on the ConvNet have been proposed for synthesizing realistic static images [13], [14], [15], [16], [17].”
A Style-Based Generator Architecture for Generative Adversarial Networks (2018, background): “A few authors have considered feeding parts of the latent code to multiple generator layers [8, 4].”
Large Scale GAN Training for High Fidelity Natural Image Synthesis (2018, background): “Previous works (Goodfellow et al., 2014; Denton et al., 2015) have considered variants of this concept; our contribution is a minor modiﬁcation of this design.”
Progressive Growing of GANs for Improved Quality, Stability, and Variation (2017, background): “While the quality of our results is generally high compared to earlier work on GANs, and the training is stable in large resolutions, there is a long way to true photorealism.”
Conditional Image Generation with PixelCNN Decoders (2016, background): “…as providing excellent samples, this network has the advantage of returning explicit probability densities (unlike alternatives such as generative adversarial networks [6, 3, 19]), making it straightforward to apply in domains such as compression [32] and probabilistic planning and exploration [2].”
Improved Techniques for Training GANs (2016, background): “Several recent papers focus on improving the stability of training and the resulting perceptual quality of GAN samples [2, 3, 5, 6].”
Density estimation using Real NVP (2016, background): “Successfully trained GAN models [17, 12, 40] can consistently generate sharp and realistically looking samples [31].”
Towards Conceptual Compression (2016, background): “GANs have been demonstrated to be able to generate realistic looking images (Denton et al., 2015; Rad-ford et al., 2015), with properly aligned edges, using a simple feedforward generative network (Radford et al., 2015).”
Generative Adversarial Networks (2021, neutral): “GANs are typically trained using a 2-player minimax game, where a Generator Network learns to produce Synthetic Data samples, and a Discriminator Network learns to differentiate between Real Data and Synthetic Data samples.”
On Buggy Resizing Libraries and Surprising Subtleties in FID Calculation (2021, background): “One idea is to conduct user studies on cloud-sourcing platforms for either assessing the samples’ image quality [17, 64, 82] or identifying duplicate images [2].”
Image-to-Image Translation with Conditional Adversarial Networks (2016, background): “Prior and concurrent works have conditioned GANs on discrete labels [38, 21, 12], text [43], and, indeed, images.”
Generative Adversarial Text to Image Synthesis (2016, methodology): “…the object category encoded into a vector (Farhadi et al., 2009; Kumar et al., 2009; Parikh & Grauman, 2011; Lampert et al., 2014), in particular to enable zero-shot visual recognition (Fu et al., 2014; Akata et al., 2015), and recently for conditional image generation (Yan et al., 2015).”