The present and future of post production business and technology | Philip Hodgetts

Apr/19

18

Resolve 16 and Machine Learning Thoughts

While I’m still to see a demo, there are few announced features that I definitely think are in the right direction, particularly those driven by Resolve’s “Neural Engine.” It seems, like Adobe Sensei and Apple’s CoreML, to be a playback engine that implements the Machine Learning models in practical tools.

Improved retiming, facial recognition, color matching, color balance and upscaling are the first implemented features. These are in line with what I have been expecting from ML: smart features that make the process easier for editors. All Resolve’s current Neural Engine driven features are better ways (faster) to do things we’ve been doing for years (other than facial recognition).

Adobe have already implemented ML driven features in their apps, and marketing tools. I’d hope that Avid have taken likely future use of ML into account in their NAB-announced revamp of Media Composer, although I doubt we’ll see any ML driven features there for many years to come, for two reasons. The Media Composer market is largely not ready for it, and Avid will have enough on their plate bringing a newly rewritten version to maturity. I expect we’ll see ML in Media Central before any desktop app.

Apple have made very good use of ML across all their products. It’s why Apple Mail predicts mailboxes for you, among dozens of little features across their devices. The have an excellent playback engine in CoreML, and developers of macOS or iOS have access to some of IBM Watson’s models. The Pro Apps team were also advertising a position for a Machine Learning specialist in late 2017.

Thanks to the Content Auto Analysis (that no-one uses) they even have a pipeline within the app to bring ML derived keywords into the app.

I’m sure we’ll see ML driven tools in FCP X at some future time. It largely depends on the priorities within the Pro Apps Team. I’d love to see a big focus on ML in a future FCP X, but there are those who would rather see collaboration, dupe detection or scrolling timelines.

No tags

2 comments

  • Richard Starkey · April 25, 2019 at 4:47 am

    Hi Philip, I’ve had to start stalking you on your website because I no longer get to hear the T&P show.
    One question: is Avid’s Phrasefind (and Scriptsynch) not considered AI or ML?

    Reply

    • Author comment by Philip · April 25, 2019 at 9:30 am

      We have some new T&P shows for me to publish. Avid’s (actually Nexidia’s) Phrasfind and ScriptSync alignment are NOT AI or ML, and for Tim Clapham to claims so at the advanced technology stage at IBC last year was beyond embarrassing! Nexidias technology is nearly 15 years old and remarkable for its time, but that predates ML and modern AI by about a decade! Not only the it is algorithmic. There was no machine learning used anywhere in the process.

      Machine Learning leads to speech to text, emotion extraction and keyword, entity and sign extraction. Nexidia’s technology matches an expected waveform with the waveforms in the audio. No understanding or meaning extracted.

      Reply

Leave a Reply

<<

>>

April 2019
M T W T F S S
« Jan   May »
1234567
891011121314
15161718192021
22232425262728
2930