Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks Supplementary Material
نویسندگان
چکیده
To describe the log-likelihood computation in our model, let us consider a two scale pyramid for the moment. Given a (vectorized) j × j image I , denote by l = d(I) the coarsened image, and h = I − u(d(I)) to be the high pass. In this section, to simplify the computations, we use a slightly different u operator than the one used to generate the images displayed in Figure 3 of the paper. Namely, here we take d(I) to be the mean over each disjoint block of 2× 2 pixels, and take u to be the operator that removes the mean from each 2× 2 block. Since u has rank 3d/4, in this section, we write h in an orthonormal basis of the range of u, then the (linear) mapping from I to (l, h) is unitary. We now build a probability density p on Rd2 by p(I) = q0(l, h)q1(l) = q0(d(I), h(I))q1(d(I)); in a moment we will carefully define the functions qi. For now, suppose that qi ≥ 0, ∫ q1(l) dl = 1, and for each fixed l, ∫ q0(l, h) dh = 1. Then we can check that p has unit integral: ∫
منابع مشابه
Improvement of generative adversarial networks for automatic text-to-image generation
This research is related to the use of deep learning tools and image processing technology in the automatic generation of images from text. Previous researches have used one sentence to produce images. In this research, a memory-based hierarchical model is presented that uses three different descriptions that are presented in the form of sentences to produce and improve the image. The proposed ...
متن کاملDeep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
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]. Samp...
متن کاملAutomatic Colorization of Grayscale Images Using Generative Adversarial Networks
Automatic colorization of gray scale images poses a unique challenge in Information Retrieval. The goal of this field is to colorize images which have lost some color channels (such as the RGB channels or the AB channels in the LAB color space) while only having the brightness channel available, which is usually the case in a vast array of old photos and portraits. Having the ability to coloriz...
متن کاملDeep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution Supplementary Material
In this supplementary document, we present additional results to complement the paper. First, we provide the detailed configurations and parameters of the proposed LapSRN. Second, we show the comparisons with the network architecture of LAPGAN [3] and the adversarial loss training. We also provide analysis on different training datasets used in existing methods. Third, we present the run time e...
متن کاملHand Grasp Image Generation Using Generative Adversarial Networks
Recent advances in deep neural networks have pushed many computer vision research areas forward dramatically. Most of these works are based on discriminative models for classification or detection problems. In this project, we are interested in using deep neural networks for generative models. In particular, we seek to train deep networks to automatically generate images of hands with particula...
متن کامل