Author name: Junjie Wen, Junlin He, Fei Ma, Jinqiang Cui

PLAF: Pixel-wise Language-Aligned Feature Extraction for Efficient 3D Scene Understanding

Junjie Wen, Junlin He, Fei Ma, Jinqiang Cui / April 24, 2026

arXiv:2604.15770v2 Announce Type: replace
Abstract: Accurate open-vocabulary 3D scene understanding requires semantic representations that are both language-aligned and spatially precise at the pixel level, while remaining scalable when lifted to 3D s…

cs.CV, cs.RO

PLAF: Pixel-wise Language-Aligned Feature Extraction for Efficient 3D Scene Understanding

Junjie Wen, Junlin He, Fei Ma, Jinqiang Cui / April 20, 2026

arXiv:2604.15770v1 Announce Type: cross
Abstract: Accurate open-vocabulary 3D scene understanding requires semantic representations that are both language-aligned and spatially precise at the pixel level, while remaining scalable when lifted to 3D spa…