Anti-aliasing for real-time applications in 3D using deep convolutional neural network
This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2020.
| Principais autores: | , , |
|---|---|
| Outros Autores: | |
| Formato: | Tese |
| Idioma: | English |
| Publicado em: |
Brac University
2021
|
| Assuntos: | |
| Acesso em linha: | http://dspace.bracu.ac.bd/xmlui/handle/10361/14437 |
| id |
10361-14437 |
|---|---|
| record_format |
dspace |
| spelling |
10361-144372022-01-26T10:20:07Z Anti-aliasing for real-time applications in 3D using deep convolutional neural network Siam, F. M. Jamius Prince, Zahidul Islam Bari, Ahmed Na sul Uddin, Jia Department of Computer Science and Engineering, Brac University Anti-aliasing Fxaa, Msaa Image processing Convolutional Neural Network Psnr Machine learning This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2020. Cataloged from PDF version of thesis. Includes bibliographical references (pages 42-44). In this paper we present a convolutional neural network model for solving the long- standing aliasing problem in the real time 3D graphics industry. Aliasing refers to the problem of having hard jagged edges in the rendered scene. These jagged edges become a distraction and on a large enough amount, creates an unpleasant viewing experience. There are quite a few techniques out there to counter this problem, namely, FXAA, NFAA, DLAA. Our neural network architecture consists of two-dimensional convolutional layers and max pooling layers for reducing the spatial dimension. We then generate the nal output from transposed convolutional layer. Our model is trained on a specialized (trained on a per application basis) and generalized (trained on a variety of dataset to work on all possible conditions) version for anti-aliasing. Based on SSIM and PSNR scores we found out that a specialized version of our model works best, both in terms of visual score and image quality metrics. F. M. Jamius Siam Zahidul Islam Prince Ahmed Na sul Bari B. Computer Science 2021-05-29T07:14:55Z 2021-05-29T07:14:55Z 2020 2020-04 Thesis ID 16101234 ID 16101172 ID 16101237 http://dspace.bracu.ac.bd/xmlui/handle/10361/14437 en Brac University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. 44 Pages application/pdf Brac University |
| institution |
Brac University |
| collection |
Institutional Repository |
| language |
English |
| topic |
Anti-aliasing Fxaa, Msaa Image processing Convolutional Neural Network Psnr Machine learning |
| spellingShingle |
Anti-aliasing Fxaa, Msaa Image processing Convolutional Neural Network Psnr Machine learning Siam, F. M. Jamius Prince, Zahidul Islam Bari, Ahmed Na sul Anti-aliasing for real-time applications in 3D using deep convolutional neural network |
| description |
This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2020. |
| author2 |
Uddin, Jia |
| author_facet |
Uddin, Jia Siam, F. M. Jamius Prince, Zahidul Islam Bari, Ahmed Na sul |
| format |
Thesis |
| author |
Siam, F. M. Jamius Prince, Zahidul Islam Bari, Ahmed Na sul |
| author_sort |
Siam, F. M. Jamius |
| title |
Anti-aliasing for real-time applications in 3D using deep convolutional neural network |
| title_short |
Anti-aliasing for real-time applications in 3D using deep convolutional neural network |
| title_full |
Anti-aliasing for real-time applications in 3D using deep convolutional neural network |
| title_fullStr |
Anti-aliasing for real-time applications in 3D using deep convolutional neural network |
| title_full_unstemmed |
Anti-aliasing for real-time applications in 3D using deep convolutional neural network |
| title_sort |
anti-aliasing for real-time applications in 3d using deep convolutional neural network |
| publisher |
Brac University |
| publishDate |
2021 |
| url |
http://dspace.bracu.ac.bd/xmlui/handle/10361/14437 |
| work_keys_str_mv |
AT siamfmjamius antialiasingforrealtimeapplicationsin3dusingdeepconvolutionalneuralnetwork AT princezahidulislam antialiasingforrealtimeapplicationsin3dusingdeepconvolutionalneuralnetwork AT bariahmednasul antialiasingforrealtimeapplicationsin3dusingdeepconvolutionalneuralnetwork |
| _version_ |
1814309200057073664 |