scholarly journals Deep Rendering Graphics Pipeline

2021 ◽  
Author(s):  
Mark Wesley Harris ◽  
Sudhanshu Semwal
Keyword(s):  
Computational Design ◽  
Production Quality ◽  
Complex Problem ◽  
Limiting Factor ◽  
Text And Image ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
3D Scene ◽  
Rendering Pipeline ◽  
Graphics Rendering

The graphics rendering pipeline is key to generating realistic images, and is a vital process of computational design, modeling, games, and animation. Perhaps the largest limiting factor of rendering is time; the processing required for each pixel inevitably slows down rendering and produces a bottleneck which limits the speed and potential of the rendering pipeline. We applied deep generative networks to the complex problem of rendering an animated 3D scene. Novel datasets of annotated image blocks were used to train an existing attentional generative adversarial network to output renders of a 3D environment. The annotated Caltech-UCSD Birds-200-2011 dataset served as a baseline for comparison of loss and image quality. While our work does not yet generate production quality renders, we show how our method of using existing machine learning architectures and novel text and image processing has the potential to produce a functioning deep rendering framework

scholarly journals Neutral-to-emotional voice conversion with cross-wavelet transform F0 using generative adversarial networks

2019 ◽  
Vol 8 ◽  
Author(s):  
Zhaojie Luo ◽  
Jinhui Chen ◽  
Tetsuya Takiguchi ◽  
Yasuo Ariki
Keyword(s):  
Wavelet Transform ◽  
Training Model ◽  
Voice Conversion ◽  
Generative Adversarial Networks ◽  
Limiting Factor ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Cross Wavelet Transform ◽  
Voice Data ◽  
Cross Wavelet

AbstractIn this paper, we propose a novel neutral-to-emotional voice conversion (VC) model that can effectively learn a mapping from neutral to emotional speech with limited emotional voice data. Although conventional VC techniques have achieved tremendous success in spectral conversion, the lack of representations in fundamental frequency (F0), which explicitly represents prosody information, is still a major limiting factor for emotional VC. To overcome this limitation, in our proposed model, we outline the practical elements of the cross-wavelet transform (XWT) method, highlighting how such a method is applied in synthesizing diverse representations of F0 features in emotional VC. The idea is (1) to decompose F0 into different temporal level representations using continuous wavelet transform (CWT); (2) to use XWT to combine different CWT-F0 features to synthesize interaction XWT-F0 features; (3) and then use both the CWT-F0 and corresponding XWT-F0 features to train the emotional VC model. Moreover, to better measure similarities between the converted and real F0 features, we applied a VA-GAN training model, which combines a variational autoencoder (VAE) with a generative adversarial network (GAN). In the VA-GAN model, VAE learns the latent representations of high-dimensional features (CWT-F0, XWT-F0), while the discriminator of the GAN can use the learned feature representations as a basis for a VAE reconstruction objective.

ORGANIC (1).pdf

2017 ◽  
Author(s):  
Benjamin Sanchez-Lengeling ◽  
Carlos Outeiral ◽  
Gabriel L. Guimaraes ◽  
Alan Aspuru-Guzik
Keyword(s):  
Machine Learning ◽  
Learning Community ◽  
Chemical Species ◽  
Material Design ◽  
Organic Photovoltaic ◽  
Generative Adversarial Networks ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Adversarial Networks ◽  
Photovoltaic Material

Molecular discovery seeks to generate chemical species tailored to very specific needs. In this paper, we present ORGANIC, a framework based on Objective-Reinforced Generative Adversarial Networks (ORGAN), capable of producing a distribution over molecular space that matches with a certain set of desirable metrics. This methodology combines two successful techniques from the machine learning community: a Generative Adversarial Network (GAN), to create non-repetitive sensible molecular species, and Reinforcement Learning (RL), to bias this generative distribution towards certain attributes. We explore several applications, from optimization of random physicochemical properties to candidates for drug discovery and organic photovoltaic material design.

Role of General Adversarial Networks in Mammogram Analysis: A Review

2020 ◽  
Vol 16 (7) ◽  
pp. 863-877
Author(s):  
Annapoorani Gopal ◽  
Lathaselvi Gandhimaruthian ◽  
Javid Ali
Keyword(s):  
Breast Tumor ◽  
Deep Neural Networks ◽  
Training Data ◽  
Learning Technology ◽  
Breast Cancers ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Adversarial Networks ◽  
Tumor Extraction

The Deep Neural Networks have gained prominence in the biomedical domain, becoming the most commonly used networks after machine learning technology. Mammograms can be used to detect breast cancers with high precision with the help of Convolutional Neural Network (CNN) which is deep learning technology. An exhaustive labeled data is required to train the CNN from scratch. This can be overcome by deploying Generative Adversarial Network (GAN) which comparatively needs lesser training data during a mammogram screening. In the proposed study, the application of GANs in estimating breast density, high-resolution mammogram synthesis for clustered microcalcification analysis, effective segmentation of breast tumor, analysis of the shape of breast tumor, extraction of features and augmentation of the image during mammogram classification have been extensively reviewed.

scholarly journals Realistic Sonar Image Simulation Using Generative Adversarial Network

2019 ◽  
Vol 52 (21) ◽  
pp. 291-296 ◽  
Author(s):  
Minsung Sung ◽  
Jason Kim ◽  
Juhwan Kim ◽  
Son-Cheol Yu
Keyword(s):  
Image Simulation ◽  
Generative Adversarial Network ◽  
Sonar Image ◽  
Adversarial Network
Sign in / Sign up

Export Citation Format

Share Document