VI3 anchors pretrained 3D foundation models to metric scale using only IMU readings

zhenjun_zhao · x · 2026-09-05

A model-agnostic framework from Javier Civera's group that metrically anchors pretrained 3D foundation models using only IMU readings. By preintegrating IMU data into a metric motion reference, VI3 recovers the scale of 3DFM outputs without ground-truth supervision, with adaptable anchoring strategies for different architectures. Experiments on synthetic and real aerial datasets show it preserves geometric consistency, acting as fine refinement under well-conditioned motion and a strong prior otherwise.

Original post →

More from Research

Research channel →