![]() ![]() We’ve seen people doing all sorts of really cool things with it – style transfers, deep fakes, deblurs, and applying full lighting effects to normal renders.”įLAME GOES AI WITH MATCH MOVE 3D CAMERA SOLVER CAMERA ANALYSISĪutodesk, similarly, has introduced several machine learning approaches into its compositing package, Flame. “That means if you have reference images for where you’re starting and what you want the result to look like, you can train an ML network to do that for you. Salazar adds that Cop圜at is not simply just a cleanup tool, and that it can generate any image-to-image machine learning network. The network he trained fixed the focus slip and made the whole frame range usable.” Ben realized that by taking pieces of the frame while they were in focus, and the same pieces of the frame when they were out of focus, he could train an ML network to make the out-of-focus frames look like the in-focus frames. “It’s the kind of shot where you’d have to cut when the focus slipped and be locked to the frame range that was in focus. “He was working with a shot where the focus slipped for a few frames,” recalls Salazar. Now, it probably won’t work for any other shots, but that doesn’t matter you’ve solved your specific problem and you’ve done 100 frames of really tricky cleanup, but only painted five or so frames manually – the rest is done by the computer.”Ĭop圜at came about when Foundry Research Engineering Manager Ben Kent, as part of Foundry’s Artificial Intelligence Research (AIR) team, was investigating how to develop a machine learning deblur. “Once you run that network on your shot,” continues Salazar, “using the new Inference node, that object will be removed from every frame. With that data and a bit of training time, Cop圜at can train a machine learning algorithm whose only job is to remove that specific object from that specific shot. You could do that cleanup on four or five carefully chosen frames, and pass those into Cop圜at along with the original, un-cleaned-up versions of those frames. ![]() “Say you have a really difficult object removal to do on a 100-frame shot. “The easiest way to think about it is with, for example, a cleanup shot,” outlines Juan Salazar, Nuke Product Manager at Foundry. In particular, Foundry’s Nuke, in conjunction with Cop圜at, allows you to orchestrate bespoke training for machine learning networks specific to individual compositing problems. NUKE’S CUSTOM MACHINE LEARNING NETWORKS WITH COPYCATĪ number of compositing tools have adopted machine learning and AI techniques to enhance image processing. Some of these features involve machine learning or AI techniques, while others deal with specific workflow speed-ups. Here, we talk to representatives from Foundry (Nuke), Autodesk (Flame), Blackmagic Design (Fusion) and Adobe (After Effects), who each highlight a new or prominent feature in their respective compositing toolset. So you may not be overly familiar with the latest features in some other compositing software that can help improve your productivity.īy identifying some key new features of the most popular compositing tools out there right now, you can find out about a useful feature or workflow in a tool you don’t currently use. If you’re a visual effects compositor, you may tend to stick mostly to just one tool for your 2D work. ![]()
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |