Hein H. Aung Matt Anderson, Advisor Introduction

Slides:



Advertisements
Similar presentations
Unsupervised Learning Clustering K-Means. Recall: Key Components of Intelligent Agents Representation Language: Graph, Bayes Nets, Linear functions Inference.
Advertisements

Internet Vision - Lecture 3 Tamara Berg Sept 10. New Lecture Time Mondays 10:00am-12:30pm in 2311 Monday (9/15) we will have a general Computer Vision.
3D Game Programming All in One By Kenneth C. Finney.
Comp 5013 Deep Learning Architectures Daniel L. Silver March,
Hurieh Khalajzadeh Mohammad Mansouri Mohammad Teshnehlab
Intelligent Database Systems Lab 國立雲林科技大學 National Yunlin University of Science and Technology 1 On-line Learning of Sequence Data Based on Self-Organizing.
Neural Network Implementation of Poker AI
Generative Adversarial Nets ML Reading Group Xiao Lin Jul
Conditional Generative Adversarial Networks
When deep learning meets object detection: Introduction to two technologies: SSD and YOLO Wenchi Ma.
Reinforcement Learning
Generative Adversarial Nets
Deep Learning for Dual-Energy X-Ray
Environment Generation with GANs
Deep Neural Net Scenery Generation
Deep Learning Amin Sobhani.
Deep Learning for Program Repair
Machine Learning & Deep Learning
Compact Bilinear Pooling
Chilimbi, et al. (2014) Microsoft Research
Week 3 (June 6 – June10 , 2016) Summary :
Photorealistic Image Colourization with Generative Adversarial Nets
Generative Adversarial Networks
Image Recognition. Contents: Motivation Objective Definition Introduction Preprocessing / Edge Detection Neural Networks in Image Recognition Practical.
CSCI 5922 Neural Networks and Deep Learning Generative Adversarial Networks Mike Mozer Department of Computer Science and Institute of Cognitive Science.
Adversaries.
Classification with Perceptrons Reading:
Synthesis of X-ray Projections via Deep Learning
A VERY Brief Introduction to Convolutional Neural Network using TensorFlow 李 弘
Sujay Yadawadkar, Virginia Tech
Li Fei-Fei, UIUC Rob Fergus, MIT Antonio Torralba, MIT
Generative adversarial networks (GANs) for edge detection
Artificial Intelligence in Healthcare
Adversarially Tuned Scene Generation
A brief introduction to neural network
Print slides for students reference
Low Dose CT Image Denoising Using WGAN and Perceptual Loss
State-of-the-art face recognition systems
Deep Learning Tutorial
ECE 599/692 – Deep Learning Lecture 1 - Introduction
Deep learning Introduction Classes of Deep Learning Networks
[Figure taken from googleblog
David Healey BYU Capstone Course 15 Nov 2018
Using Tensorflow to Detect Objects in an Image
Image to Image Translation using GANs
Age and Gender Classification using Convolutional Neural Networks
GAN Applications.
Outline Background Motivation Proposed Model Experimental Results
Lip movement Synthesis from Text
Depth Aware Inpainting for Novel View Synthesis Jayant Thatte
Presented by Wanxue Dong
Attack and defense on learning-based security system
Recent Advances in Generative Adversarial Networks (GAN)
Zhedong Zheng, Liang Zheng and Yi Yang
Textual Video Prediction
Presentation By: Eryk Helenowski PURE Mentor: Vincent Bindschaedler
Neural Network Pipeline CONTACT & ACKNOWLEDGEMENTS
Adversarial Learning for Security System
TPGAN overview.
Ch 14. Generative adversarial networks (GANs) for edge detection
Automatic Handwriting Generation
Introduction to Neural Networks
VERY DEEP CONVOLUTIONAL NETWORKS FOR LARGE-SCALE IMAGE RECOGNITION
Angel A. Cantu, Nami Akazawa Department of Computer Science
Cengizhan Can Phoebe de Nooijer
Text-to-speech (TTS) Traditional approaches (before 2016) Neural TTS
End-to-End Speech-Driven Facial Animation with Temporal GANs
Adrian E. Gonzalez , David Parra Department of Computer Science
Generative adversarial networks (GANs)
An introduction to neural network and machine learning
Presentation transcript:

Generative Adversarial Networks for Dynamic Rendering of Terrain Textures Hein H. Aung Matt Anderson, Advisor Introduction Currently, most of the game world environments are hand-crafted by game designers. This greatly limits the extent to which the player can travel around since the human designer can only build the static game worlds to a limited extent. However, being able to train machine learning algorithms to learn about terrains is going to allow the game to dynamically generate new areas in the game. Analysis of Evaluations The results indicate that my GAN is capable of generating grass and pebbles since more than 75% think the generated images are real. For pavement and cracked ground, less than 50% of the evaluators thinks they don’t look realistic. In total, 56% of the Evaluators think the images are realistic. Figure 3. Generative Adversarial Network (conceptual) [1][2][3][4] Generator creates image with random pixels and they are sent into the discriminator. The discriminator will compare these images with real images and decide if thy are fake or not. Methodology I sent out Google Forms with 30 generated images [4]. The evaluators are asked to write a short text description of each image. After I collected responses from 20 evaluators, I started analyzing (Table [1]). Table 1: A score distribution of four categories showing the best and the worst scores of all four. Figure 1: No Man Sky, one of the games that uses procedural generation of terrains and has never-ending environment. Algorithm & Results real_image = random_image random_Input = random_Dimension fake_image = generator(random_Input) real_result = discriminator(real_image) fake_result = discriminator(fake_image) D_loss = fake_result - real_result G_loss = - fake_result while i <= Epoch do \\ Epoch = 2000 while j <= batch do \\ batch = 16 Update discriminator (D_loss) Update generator (G_loss) Future Work I have limitations in my thesis, such as scale variation of input images. Due to the difference in the height of the images that was taken, the scale of objects in images are varied. I planned to find datasets that have the same scale. Moreover, the design of evaluation can be done better by using check box options for evaluators. Due to the freedom of text I have given to the evaluators, the a few of the responses were not helpful to analyze the evaluations. Objective: Can we create a generative adversarial networks (GANs) to dynamically render new images for different types of ground terrain textures (such as soil, grass plains). Given an input image, the GAN created will re-render a set of different variations images that is set on the original input terrain texture [1]. I created GAN based on Leon Gatys’[2] network algorithms (discriminator and generator) and the training algorithm is based on Raval’s pokeGAN training algorithm. Acknowledgments I would like to acknowledge Akshay Kashyap on the course for Deep Learning and CSC-231ln. Also David Frey for helping me out in CROCHET lab References [1] Grigory Antipov, Moez Baccouche, Jean-Luc Dugelay. Face aging with conditional Generative Adversarial Networks. 7, 2017 [2] Leon Gatys, Alexander Ecker, and Matthias Bethge. Texture synthesis using convolutional neural networks. In Advances in Neural Information Processing Systems 28, 2015 [3] Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. “Generative Adversarial Nets”. In: (2014). [4] Bengio, Y. (2009). Learning deep architectures for AI. Now Publishers [5] Siraj Raval. Generative Adversarial Networks. 2017. Github. [6] CSC-231n. CS23ln Convolutional Neural Networks for Visual Recognition. 2017. Stanford online course. Figure 2: 4 categories are chosen. (1)cracked ground, (2)pebbles, (3)grass, (4) pavement as datasets Figure 4: Generated Images of cracked ground, pebbles, grass, pavement at a certain point of loss value and a certain iterations