Artificial intelligence in digital visual effects

Visual effects (VFX) are today’s special effects in films brought about by digitisation. Due to the increased accessible number of tools and technologies available the creation, manipulation and illusion of such effects continuously develop in photorealism and believability. Visual effects have been...

Full description

Saved in:
Bibliographic Details
Main Author: Ong, Victor
Other Authors: Benjamin Seide
Format: Thesis-Master by Research
Language:English
Published: Nanyang Technological University 2021
Subjects:
Online Access:https://hdl.handle.net/10356/151632
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-151632
record_format dspace
spelling sg-ntu-dr.10356-1516322023-03-11T20:02:55Z Artificial intelligence in digital visual effects Ong, Victor Benjamin Seide School of Art, Design and Media BSeide@ntu.edu.sg Visual arts and music::Film Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Visual effects (VFX) are today’s special effects in films brought about by digitisation. Due to the increased accessible number of tools and technologies available the creation, manipulation and illusion of such effects continuously develop in photorealism and believability. Visual effects have been used to create imaginative and realistic characters, or even replace actors and backgrounds using techniques that result in an almost seamless integration that appear as if shot with the live-action elements. Looking to the future, Artificial Intelligence (AI) development is growing. These deep learning systems can greatly assist if not, replace existing visual effects industry processes. The automation of rotoscoping in the case of Rotobot allows the reduction of industry-wide straightforward but laborious processes. Deep Video Portraits, also commonly known as deepfakes, will allow AI to process the facial movements data from a source actor to move facial features of a still portrait image of a target actor with realistic results. This dissertation investigates the possibilities when AI applications can be used in the field of visual effects - How will laborious or complex tasks be done differently to ease production time and improve efficiency or cost-effectiveness, leading to the outlook that most of the established visual effects workflows could eventually be replaced. Does having accessible AI technology in the future mean anyone outside of the visual effects profession can create high-quality film effects? It is this exploration that asks the question: How will the visual effects industry change with AI? Master of Arts 2021-06-25T06:43:12Z 2021-06-25T06:43:12Z 2021 Thesis-Master by Research Ong, V. (2021). Artificial intelligence in digital visual effects. Master's thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/151632 https://hdl.handle.net/10356/151632 10.32657/10356/151632 en This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0). application/pdf Nanyang Technological University
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Visual arts and music::Film
Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
spellingShingle Visual arts and music::Film
Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
Ong, Victor
Artificial intelligence in digital visual effects
description Visual effects (VFX) are today’s special effects in films brought about by digitisation. Due to the increased accessible number of tools and technologies available the creation, manipulation and illusion of such effects continuously develop in photorealism and believability. Visual effects have been used to create imaginative and realistic characters, or even replace actors and backgrounds using techniques that result in an almost seamless integration that appear as if shot with the live-action elements. Looking to the future, Artificial Intelligence (AI) development is growing. These deep learning systems can greatly assist if not, replace existing visual effects industry processes. The automation of rotoscoping in the case of Rotobot allows the reduction of industry-wide straightforward but laborious processes. Deep Video Portraits, also commonly known as deepfakes, will allow AI to process the facial movements data from a source actor to move facial features of a still portrait image of a target actor with realistic results. This dissertation investigates the possibilities when AI applications can be used in the field of visual effects - How will laborious or complex tasks be done differently to ease production time and improve efficiency or cost-effectiveness, leading to the outlook that most of the established visual effects workflows could eventually be replaced. Does having accessible AI technology in the future mean anyone outside of the visual effects profession can create high-quality film effects? It is this exploration that asks the question: How will the visual effects industry change with AI?
author2 Benjamin Seide
author_facet Benjamin Seide
Ong, Victor
format Thesis-Master by Research
author Ong, Victor
author_sort Ong, Victor
title Artificial intelligence in digital visual effects
title_short Artificial intelligence in digital visual effects
title_full Artificial intelligence in digital visual effects
title_fullStr Artificial intelligence in digital visual effects
title_full_unstemmed Artificial intelligence in digital visual effects
title_sort artificial intelligence in digital visual effects
publisher Nanyang Technological University
publishDate 2021
url https://hdl.handle.net/10356/151632
_version_ 1761781409859502080