[ECCV 2026] One Scene, Two Depths: Probing Geometric Ambiguity in Monocular Foundation Models (Layered 3D Spatial Understanding)
representation depth-estimation interpretability eccv latent-space foundation-models visual-prompting spatial-intelligence multi-layer-depth spatial-understanding eccv2026 model-bias geometric-ambiguity depth-layer-preference spatial-prompting
-
Updated
Jun 30, 2026 - Python