🛑 New Paper
PointSt3R: Point Tracking through 3D Grounded Correspondence
arxiv.org/abs/2510.26443

Can point tracking be re-formulated as pairwise frame correspondence solely?

We fine-tuning MASt3R with dynamic correspondences and a visibility loss and achieve competitive point tracking results
1/3

As Peter couldn't make it... I had to use
Google DeepMind
#Veo 3.1 to put him back in.. Using the ingredients to video new capability... These are two videos of the attempt...
Good reason for deepfakes?
2/2

This is one of the coolest ideas using EPIC-KITCHENS in a long while...
We've all been waiting to be replaced by robots! At least this is now done in the generative space...
Great work by Marion Lepert, Jiaying Fang and @leto--jean.bsky.social from Stanford IPRL.. congrats!
arxiv.org/abs/2508.09976

If you have not seen this yet, you are missing a lot!
Genie 3 by Google DeepMind was unveiled today &delivers in abundance.
Of course my fav example is ego x world model.
It is video gen x modeling "out of the frame".
Many congrats @jparkerholder.bsky.social & team
deepmind.google/discover/blo...