Announcement
LEDGER promises 3D object memory without looking back at first-person videos
A post introducing LEDGER says it remembers where objects were, when they moved and what they held.
TLDR
LEDGER is introduced as persistent 3D object memory built from egocentric, or first-person, videos. The post claims it can answer questions about objects and their movements without looking back at the video.
Combined views
2K
1 Source, first seen ago
