LoGeR – 3D reconstruction from extremely long videos (DeepMind, UC Berkeley)

msuniverse2026

Truly don't understand what is happening in the heads of these researchers. Can't they see how the main use of this is going to be mass surveillance?

IshKebab

Very cool. Doesn't seem like they've actually released the code: > This is a reimplementation of LoGeR; complete code and models will be released upon approval. I don't understand why it's a re implementation either? I would guess it's "research" code anyway so not really usable unless you are an expert.

Dead_Lemon

What is the actual objective of this, is it solving an issue or creating a solution to a problem, that is still to be determined? It seems like a lot of energy to replicate a lidar mapping system. It's not like you can expect accurate dimensions from this approximate guess work, excluding the expected hallucinations adding to inaccuracy.

tmilard

Very interesting paper. I can see street-view using it to perfect the 3D analysing of the photo-video they catch with there google-car. What a wonderfull time we are living in ! Specificaly in the Video to 3D reconstruction. Every month, a new brick is put in place.Super

_fw

This is like something straight out of Cyberpunk 2077 - the braindances investigation scenes.

priowise

very interesting direction. One thing I’m curious about with extremely long videos is how you handle temporal drift over time. Do you periodically re-anchor the reconstruction or rely purely on accumulated frame consistency?