New on Hugging Face — CoTracker simultaneously tracks the movement of multiple points in videos using a flexible design based on a transformer network — it models correlation of the points in time via specialized attention layers. 🤗 Try CoTracker ➡️

CoTracker can track every pixel in a video, points sampled on a regular grid on any video frame or manually selected points. In our testing it compares favorably against state-of-the-art point tracking methods in both efficiency & accuracy. Code ➡️

@huggingface I attempted this on a piece of AI-generated footage, and it perfectly tracked the camera moves, the background, part of the movement of the person. This is incredible.

@huggingface Nyan Cat vibes!

@huggingface What are potential use cases for this type of tech?

@huggingface

@huggingface Interesting, point tracking in MMA/Boxing comes to mind

@huggingface Do you need to identify the object or it’s done automatically?

@huggingface How much climate damage will this model cause? @huggingface says that's all they can think about.

@huggingface Moon

@huggingface LGBT 🚫 🆗️