Real time image animation in opencv using first order model

Re:Real time image animation in opencv using first order model by rozgo on Tuesday May 26, 2020 @02:15PM (#23314544)

It's incredibly satisfying to reproduce these papers. I now make Rust versions of the most interesting projects. And try to make low-latency inference pipelines for those that show potential for real-time use. Some are sketched out here: https://github.com/Simbotic/SimboticTorch

The bulk of the work to get real-time working is to move more of pipeline to GPU. Mostly things handled by numpy and some image/video transformations.

[ Parent | on HN ]

Re:Real time image animation in opencv using first order model by qchris on Tuesday May 26, 2020 @04:19PM (#23315925)

That's awesome! If you're interested, there's a group working on machine learning in Rust, including some working on doing GPU pipelines for it at https://github.com/rust-ml/wg . I'm not sure if any of the work being done right now is directly applicable to any of the projects that you're reproducing, but it might be worth a look!

[ Parent | on HN ]

Re:Real time image animation in opencv using first order model by rozgo on Tuesday May 26, 2020 @06:44PM (#23317330)

Oh, I'm interested. Thanks for letting me know. Would love to contribute.

[ Parent | on HN ]

Re:Real time image animation in opencv using first order model by BracketMaster on Tuesday May 26, 2020 @07:06PM (#23317501)

This truly is amazing.

I've noticed that GPU does help a lot with inference. It would be nice if it were easier to make projects like these mobile.

Google and Apple have SDKs for running nets on phones, but its a shame its so hard to do things like this on the Raspberry pi...

[ Parent | on HN ]

Re:Real time image animation in opencv using first order model by Miraste on Wednesday May 27, 2020 @04:36PM (#23329620)

Tensorflow Lite runs on Raspberry Pis. It's even in the official docs: https://www.tensorflow.org/lite/guide/build_rpi

[ Parent | on HN ]