Thinking in Blender: Staged Executable Inverse Graphics with Vision-Language Models 事件

Thinking in Blender: Staged Executable Inverse Graphics with Vision-Language Models arXiv:2606.02580v1 Announce Type: new Abstract: Inverse graphics is a longstanding and highly underconstrained problem that seeks to reconstruct images as editable 3D scenes which can be rendered, relit, and manipulated. In this work, we investigate whether pretrained vision-language models (VLMs) can perform executable inverse graphics directly from a single image by reconstructing a scene as an editable Blende