ECCV Paper Proposes MVAP-G to Attack Visual Geometry Transformers

An ECCV 2026 oral paper, MVAP-G, introduces a method for generating multi-view adversarial examples that deceive the VGGT visual geometry transformer, exposing vulnerabilities in 3D vision foundation models.

2026-08-25 ~ 2026-08-25 · 2 related posts

• MVAP-G paper demonstrates fooling Visual Geometry Grounded Transformers — kwangmoo_yi · 2026-08-25
• MVAP-G: Generating Multi-view Adversarial Examples for VGGT (ECCV'26) — kwangmoo_yi · 2026-08-25