Making SAM 2 run 2x faster

[mvoodarla]

I was pretty amazed with SAM 2 when it came out given all the work I do with video. My company works a ton with it and we decided to take a crack at optimizing it, and we made it run 2x faster than the original pipeline!

Unlike LLMs, video models are notorious for incredibly inefficient file reading, storage, and writing which makes them much slower than they need to be.

We wrote a bit about our work here and thought we'd share with the community:
https://www.sievedata.com/blog/meta-segment-anything-2-sam2-introduction

[rentainhe]

Awesome work! It will be much more convenient for community users to annotate their own datasets.

[MonolithFoundation]

@mvoodarla Are there merely advertisements for your cloud services? No code? Additionally, I didn't see any substantive content in the blog.

[mvoodarla]

Hey! We're doing a follow up blog soon with technical details as well.