PRODUCTION/POSTAI AND MACHINE LEARNING IN VFX VFX VIRTUAL PRODUCTION


Framestore created the Taweret character in Moon Knight using an inhouse ML tool which dynamically simulates facial shapes. The opposi te page shows the comple ted character


any of the visually cumbersome dots and markers on their faces, and use AI to fully track and reconstruct a 3d performance of the face. This technique, often used in conjunction with faceswap and additional capture technology such as Medusa and Anyma is where AI really empowers creative talent to have the most flexibility to accomplish the stories they want to tell.” There is also the ability to use


tools similar to the widely publicised Dall-E 2, Midjourney and others that use natural language programming to generate original AI-derived art (though as anyone who has used them will attest, the results can be variable at best). While these will undoubtedly help to extend the creative pallets of the artists that use them with a little wrangling, it’s worth remembering that all this is just the start. “The really exciting thing is


realising it can be applied to solve a far wider range of complex problems than initially thought,” says Morris. “It’s not just limited to image processing tools. In fact, some of the more mundane applications such as automatically categorising our vast library of image elements such as


48 80 televisual.com S tu n 2022 Aummer 2021


skies, explosions, etc to make them easier to find, are the ones that have the biggest impact for our artists.” And it doesn’t stop there. As


AI deployments move from operational to systemic and begin to spread throughout the digital fabric of vfx organisations, so they are going to have impacts way beyond just artistic tools. Benoît Maujean, Global Head of Research, Technicolor Creative Studio talks of provisioning resources based upon data analysis of previous productions, while at Cinesite, Sciolette sees it improving “the accuracy and speed of processes like bidding, scheduling, resource forecasting, and more.”


Where do people fit in? Amidst all the talk of enhanced


productivity and increased automation of repetitive tasks, there is an inevitable concern about the future of the human operators in all of this. This is an old trope dating back to the industrial revolution and the Luddite unrest of the early 18th century. History shows that


Compute intensive workflows can run 10-100 times faster than previously possible


Manne Öhrström FRAMESTORE


sometimes the concerns have proved valid and sometimes they haven’t. Maujean, for ones, believes


that they aren’t this time either, certainly not in the immediate future. “The best example here


is that Photoshop has not killed photography, or digital editing software like Avid and Premiere has not killed editing,” he says. “It might hit some intermediate jobs like traditional stock image agencies, or maybe it will drive them to some market- places-oriented businesses, but


AI will not replace artists.” His take is that you still need


someone to define and refine the concepts, as with the prompt editing to generate digital images from natural language descriptions with the likes of Dall-e 2, and then to validate and iterate with your creation and production stakeholders. “As usual, artists like to have a great variety of tools to combine them to achieve their creative goals,” he says. “It will also mean more work for software engineers to arrange and maintain datasets and interfaces with the


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