SceneTeract
_{Agentic Functional Affordances and VLM Grounding in 3D Scenes}

Léopold Maillard^1,2, Francis Engelmann^3,4 Tom Durand², Boxiao Pan³, Yang You³, Or Litany^5,6, Leonidas Guibas³, Maks Ovsjanikov^1
1École Polytechnique, ²Dassault Systèmes, ³Stanford University, ⁴USI Lugano, ⁵Technion, ⁶NVIDIA

SceneTeract is a verification engine that, given a 3D scene, an embodied agent profile, and a target activity, decomposes the task into atomic actions and validates each step with explicit geometric and physical checks, producing finegrained and actionable feasibility diagnostics.

🚧 Code and Data to be released soon!