We are back again with a recap of the best tech of 2018. As always, some things are new, some have been around, and some we’ve just starting to incorporate into our tiny little world of animation and filmmaking.
- Virtual Film Production. With game engines and real-time raytracing, virtual production is hitting its stride, and will propagate its way backward through pre-production and concept, all the way back to pitching a film. And ideally, the tools on the actual production migrates seamlessly to post-production.
- Realtime Raytracing. Nvidia released its Quadro RTX graphics card this year at SIGGRAPH. Too many applications to list, but the aforementioned virtual production is a key use, as is rapid concept development. Seeing your changes in real time with reflections, DOF and GI is a game changer.
- Sharing. With NASA releasing its archives, Disney offering up its technology as open source along with actual production assets like the island in Moana, more companies are showing that science can’t grow without collaboration, and art can’t grow without sharing.
- Quadrupedal AI Motion Analysis. Yet another example of using artificial intelligence to learn complex behaviors.
- 3D Metal Printing. No more plastic 3D prints! We needed something stronger, and we got it.
- Sensor City. We have seen the future, and it involves city planning using sampled big data from sensors to best design it for the community.
- Universal AI. Yes, they were once the playground of the rich and well-funded, but AI and machine learning have become more accessible thanks to the efforts of Amazon’s AWS, Google’s Cloud ML and Cloud AI tools.
- GANS: Dueling Neural Networks. Generative adversarial networks are what happens when two AI systems are in cahoots. One tries to make fake images based on its learned sample set. The other gives it constructive feedback based on the same sample set. Both learn more as one gets better at faking it.
- Houdini 17. Vellum, character tools, UV tools, better fluid sims, grooming tools, facial auto-rigging, built-in Bullet Solver soft constraints for collision, material-based fracturing … The list goes on and on. What’s not to love?
- Thanos. Digital Domain created a facial motion-capture system that uses deep learning to finesse in the fine details of the year’s biggest blockbuster villain.
- Disney Research’s Stuntronics. Everyone says they love real stunts. But Disney Imagineering gave us autonomous robot stunt doubles this year. Does this mean less work for real-life stunt professionals?
For those of you tech and animation nerds who like to have a crystal ball to look into the future of computer graphics and its applications, I encourage to you check out the SIGGRAPH white papers every year. Put together by brilliant academics from all over the globe, these papers fuel the software and workflows that we will all be using in the years ahead! Here’s to a fantastic new year filled with amazing new technological releases.
