Computational cinematography software for content creators and film makers. By Special Circumstances. @_vade & @rsomani95
Joined December 2015
- Tweets142
- Following15
- Followers843
- Likes164
Synopsis retweeted
Have a Panel UI for Synopsis analysis JSON parsing in After Effects now. This is a nice (albeit slow) environment to debug but also explore inference results.
Really proud of the work @rsomani95 has been doing on improving our model. Note how the composition tracks focus A+.
Synopsis retweeted
I really cant wait to run @_synopsis_ on M1 Max and see how ridiculous it is.
Synopsis retweeted
Here is a great Snapshot of our Industry Speakers taken by @raoanyi!
Joon-Young, @agermanidis, @_vade, @rsomani95, Fernando Amat, Xintao Wang
Synopsis retweeted
Special thanks to our Industry Speakers!
Joon-Young, @AdobeResearch
@agermanidis, @runwayml
@_vade @rsomani95, @_synopsis_
Fernando Amat, @NetflixResearch
Xintao Wang, Tencent!
Great insights coming from real-world applications!
#iccv2021 @ICCV_2021
Synopsis retweeted
This wouldn’t have been possible without @_synopsis_ - which has come a long way and is putting in some serious work these days.
Synopsis retweeted
We put up an article detailing the insane amount of work done for @hbomax by @HushStudios and Special Circumstances (@rsomani95 and my company which doesn’t have yet have a twitter)
If you’re curious about #ai / #ml and #film / #cinematography check It:
special-circumstances.medium…
Synopsis retweeted
Really proud of the work @rsomani95 and I did for cinematic @_synopsis_ analysis of @hbomax ’s content library on behalf for our friends at @HushStudios. The entire team worked really hard on this and it came out lovely.
New & improved models powered:
heyhush.com/work/hbo-max-the…
Synopsis retweeted
All from the same external SSD
Hackintosh w/ i9 10k 128GB Radeon VII: ~ 1:30s
MacBook Pro w eGPU 580 : ~2:15s
M1 Mac Mac mini: ~15s
No. That is not a typo. Maybe theres a new case of unified memory bugs my threading code fails on but this output seems ok?
Synopsis retweeted
So, I just got @_synopsis_ running natively on M1 Apple Silicon.
We have the 16GB Mac mini.
A 4 minute and 30 second 720p h.264 movie analyzed with a CoreML model, as well as some custom metal performance shaders:
Cc @rsomani95
Synopsis retweeted
Sneak peek: we’ve been quietly working on improving @_synopsis_ - @rsomani95 has been making huge progress on our new location data set / model. These images are sorted against only shots at the same inferred *location* :
Testing drastically improved classifiers from Fast AI into CoreML - work done by @rsomani95 / @_vade
Moonlight - car shots:
Hi friends - Synopsis Public Beta 2 is available via Sparkle auto update or via synopsis.video
If you have any feedback - bug reports or feature requests, don’t hesitate to let us know!
Happy analyzing!
Thanks for taking a look at our project!
We've been testing @_synopsis_ software for the past week or so and we really like it. It reads HAP files & converts them for MAC. One part analyzes/converts, and one part views and processes analytics. Apple users have needed this for a while!
thrasosmedia.com/synopsis/
This is *exactly* why we are building Synopsis out in the open, and have a section dedicated to bias.
You can’t make opaque algorithms to control culture, who participates in creating & representing culture.
Respectfully - this is exactly the wrong approach @cinelytic
Warner Bros has signed a deal for a AI-driven film management system which will help decision-making for greenlighting certain films. The AI system can assess an actor’s value in any territory and how much a film is expected to earn in theaters. (Source: hollywoodreporter.com/amp/ne…)
Super excited to see Synopsis out in the wild, and even more excited that what we’re working towards is becoming useful and fun to use!
Ran about 1000 sketches through synopsis.video and find the feature sort to be pretty great in finding similar forms. Editing video this week and this is super helpful
Synopsis retweeted
Running synopsis.video on my sketches overnight - super curious to see what it finds
