Perceive-then-Plan: Layout-as-Policy for Monocular 3D Scene Layout Estimation 事件

Perceive-then-Plan: Layout-as-Policy for Monocular 3D Scene Layout Estimation arXiv:2605.25326v1 Announce Type: new Abstract: Building structured 3D scene layouts from a single image requires reconciling visual observations with physical and spatial constraints, a challenge that is difficult to address with direct prediction alone. In this work, we formulate monocular 3D layout estimation as a perceive-then-plan problem with vision-language models, where a Perceiver first grounds the 3D objects