3D 视觉

LLaVA$^3$: Representing 3D Scenes like a Cubist Painter to Boost 3D Scene Understanding of VLMs

LLaVA$^3$：像立体主义画家一样表示3D场景以提升VLM的3D场景理解

Doriand Petit, Steve Bourgeois, Vincent Gay-Bellile, Florian Chabot, Loïc Barthe

专题命中 空间理解 ：3D reconstruction(abstract)；分类 cs.CV

AI总结 LLaVA$^3$通过立体主义方法提升VLM对3D场景的理解能力，利用多视角2D图像无需微调实现更优的3D场景理解。

Comments Accepted at AAAI'26