Track2Act: Predicting Point Tracks from Internet Videos enables Diverse Zero-shot Robot Manipulation

Add code
May 02, 2024
Figure 1 for Track2Act: Predicting Point Tracks from Internet Videos enables Diverse Zero-shot Robot Manipulation
Figure 2 for Track2Act: Predicting Point Tracks from Internet Videos enables Diverse Zero-shot Robot Manipulation
Figure 3 for Track2Act: Predicting Point Tracks from Internet Videos enables Diverse Zero-shot Robot Manipulation
Figure 4 for Track2Act: Predicting Point Tracks from Internet Videos enables Diverse Zero-shot Robot Manipulation

Share this with someone who'll enjoy it:

View paper onarxiv icon

Share this with someone who'll enjoy it: