Home Knowledge Base ViGeo

ViGeo

No mentions found

This entity hasn't been tracked yet, or Iris is still building its knowledge base.

Related Articles from SNS

Towards Consistent Video Geometry Estimation

arXiv:2605.30060v2 Announce Type: replace Abstract: This work presents ViGeo, a feed-forward foundation model for recovering spatially dense and temporally consistent geometry from video sequences. Built upon a plain transformer architecture without task-specific architectural modifications, ViGeo supports streaming, full-sequence, and long-video inference within a unified model. The key design is dynamic chunking attention, which exposes the model to both bidirectional and causal temporal...

arXiv CS 9d ago