PRODUCTION/POSTAI AND MACHINE LEARNING IN VFX VFX VIRTUAL PRODUCTION


A scene from The Addams Family 2 before and af ter denoising


stable workflows that can be used effectively in production.” There is also a balance to be


made between choosing whether to develop in-house or lean in on commercial solutions such as Dall-e 2. As Sciolette points out: “Being true innovators in this area is very expensive and risky. The time frame between new research being published and a broad availability of the techniques is getting shorter and shorter making it hard to justify the investment.” There are also some potentially interesting legal aspects that are yet to be fully explored in using public data sets to generate IP and exploiting that for commercial purposes.


What Skynet did next So, where is the industry heading?


As AI matures within the industry and starts to move further away from simple automation of repetitive tasks, what impacts shall we see? At Cinesite, Head of CG, Holger


Voss says that we are clearly at the beginning of a journey. “We see some incredible results coming from research at the moment and this is starting to translate into new ML based tools,” he says. “We will see


80 50 televisual.com S tu n 2022 Aummer 2021


much more of those coming in the next few years opening it up to the majority of our industry.” Michele Sciolette also


references the theme of acceleration, pointing out that the likes of Dall-e 2 would have seemed inconceivable not so long ago and have gone mainstream with extreme rapidity (as long as you can make it to the top of the waitlists that is). He’s also keenly interested in some of the results of Nvidia’s StyleGAN project, a generative adversarial network currently on its third generation which has produced some frankly astonishing 2D images that have set off moral panics about deepfakes all on their own. “Some of the work happening


around the StyleGan and style transfer techniques in general is showing incredible potential for efficiently creating new visual styles for our projects,” he says. “So far the focus has been primarily on manipulation on still frames and it will be exciting to see the potential of these techniques when extended to work on video sequences.”


Foundry’s Ring meanwhile talks


We see some incredible results coming from research at the moment


Holger Voss CINESITE


of seeing some impressive examples of ML applied to immersive scenes, name checking techniques such as NeRF (Neural Radiance Fields) and LLFs (Local Light Fields), both of which look to build novel views of 3D scenes from partial information, as well as techniques for automatic extraction of textures from images. And the sheer amount of tools coming on to the market, especially in terms of open source software libraries and frameworks, is mashing the AI accelerator ever further to the


floor. “We are using several


frameworks, such as TensorFlow and Pytorch and working within those rather than starting from scratch,” says Jellyfish’s Smith. “The natural evolution of use-


cases is proliferating very quickly, so the sky’s the limit,” concludes ILM’s Morris. “I really do think this technology is one of those rare game changers that we are only just beginning to fully understand and apply to all our existing technologies and creative challenges.”


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