PRODUCTION/POSTAI AND MACHINE LEARNING IN VFX VFX VIRTUAL PRODUCTION
Artificial Intelligence and Machine Learning will have an increasing impact throughout the production process, and it’s in vfx that the initial changes it will unleash are being felt first. Andy Stout reports
GHOSTS IN THE MACHINE
t the start of 2019, in what profoundly feels like another era now, tech analyst Gartner
published a gated report in which it mapped developments in the AI field onto its own infamous hype cycle. This creates a timeline for new technology that charts the degree of expectation (and, by implication) investment around it and runs from initial Innovation Trigger on to the drolly named Peak of Inflated Expectations and into the Trough of Disillusionment, before finally transitioning through the Slope of Enlightenment and on to the Plateau of Productivity. You get the picture. “AI is almost a definition of hype.
Yet, it is still early: New ideas will surface and some current ideas will not live up to expectations,” Gartner wrote back then. And in 2019 some of the most hyped aspects of AI were firmly sliding down into the Trough, including Computer Vision and Autonomous Vehicles. Three years later Autonomous Vehicles are still languishing there, with a tag stating they won’t be driving up onto the Plateau and away for
46 80
televisual.com S tu n 2022 Aummer 2021
over a decade. Computer Vision, however, is already over halfway up the Slope of Enlightenment and is thought to be a genuinely mass market proposition in under two years. As far as VFX is concerned, it
already is. The image processing techniques that are a part of the overall R&D effort in Computer Vision are starting to fundamentally change the industry as AI and its more powerful sibling, Machine Learning (ML — which learns from data inputs and makes accurate predictions/decisions as a result) start to have an increasing impact. “In VFX we’re starting to see
ML being used to solve previously near-impossible problems, such as replacing actors’ faces with younger versions of themselves,” comments Dan Ring, Head of Research, Foundry. “Deep face swaps, digi- doubles and avatars have been added to the studios’ toolbox over the last couple of years and are probably used more than you realise. Early pre-trained tools such as super-resolution and denoising have hit the mainstream and are now expected as default options in comp and rendering software.”
Already all pervasive Initial deployments of AI throughout
the broadcast industry (and elsewhere) have tended to focus on task automation and allowing the algorithms to do the donkey work in the background. “We believe the main driver for
the development in AI in VFX is to help with artist iteration in addition to the current staffing shortage in this industry,” says Jeremy Smith at Jellyfish Pictures. “We would rather our staff focus their time on ‘artistry’ rather than mundane tasks as artists’ time is one of the most important things that we have.” The adroit use of AI doesn’t just
free up artists’ time, either. It frees up other resources as well and can have a dramatic effect on compute expensive — and therefore cost expensive — tasks such as rendering. “In terms of optimisation and
accelerating existing workflows, the power can often be transformative,” comments Manne Öhrström, Framestore’s Global Head of Software VFX. “Compute intensive workflows can run 10-100 times faster than previously possible, and with those kinds of efficiency improvements, you can begin
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62 |
Page 63 |
Page 64 |
Page 65 |
Page 66 |
Page 67 |
Page 68 |
Page 69 |
Page 70 |
Page 71 |
Page 72 |
Page 73 |
Page 74 |
Page 75 |
Page 76 |
Page 77 |
Page 78 |
Page 79 |
Page 80 |
Page 81 |
Page 82 |
Page 83 |
Page 84 |
Page 85 |
Page 86 |
Page 87 |
Page 88 |
Page 89 |
Page 90 |
Page 91 |
Page 92 |
Page 93 |
Page 94 |
Page 95 |
Page 96 |
Page 97 |
Page 98 |
Page 99 |
Page 100 |
Page 101 |
Page 102 |
Page 103 |
Page 104 |
Page 105 |
Page 106 |
Page 107 |
Page 108 |
Page 109 |
Page 110 |
Page 111 |
Page 112 |
Page 113 |
Page 114 |
Page 115 |
Page 116 |
Page 117 |
Page 118 |
Page 119 |
Page 120 |
Page 121 |
Page 122 |
Page 123 |
Page 124 |
Page 125 |
Page 126 |
Page 127 |
Page 128 |
Page 129 |
Page 130 |
Page 131 |
Page 132 |
Page 133 |
Page 134 |
Page 135 |
Page 136 |
Page 137 |
Page 138 |
Page 139 |
Page 140 |
Page 141 |
Page 142 |
Page 143 |
Page 144 |
Page 145 |
Page 146 |
Page 147 |
Page 148 |
Page 149 |
Page 150 |
Page 151 |
Page 152 |
Page 153 |
Page 154 |
Page 155 |
Page 156
