Early-Signal Detector

model · first seen 4 Oct 2026

VGGT

Also: visual geometry transformer, Visual Geometry Grounded Transformer

A feed-forward visual geometry foundation model that predicts camera poses and depth from image sets.

Mentions per week

0319 May11 Aug10 NovPapersCodeDiscussion

PapersCodeDiscussion

Earliest sources

Latest sources

Mentioned together with

metric depth estimationpose graph loop closureclustered attentionmultiview point cloud registrationmulti-view reconstructiondeterminantal point processworld action modeluncertainty estimationtoken pruningtraining-free model acceleration