SpatialCLIP: Learning 3D-aware Image Representations from Spatially Discriminative Language.

Zehan Wang 0001 Sashuai Zhou Shaoxuan He Haifeng Huang 0001 Lihe Yang Ziang Zhang Xize Cheng Shengpeng Ji Tao Jin 0004 Hengshuang Zhao Zhou Zhao 0001 SpatialCLIP: Learning 3D-aware Image Representations from Spatially Discriminative Language. 29656-29666 2025 CVPR https://openaccess.thecvf.com/content/CVPR2025/html/Wang_SpatialCLIP_Learning_3D-aware_Image_Representations_from_Spatially_Discriminative_Language_CVPR_2025_paper.html https://doi.org/10.1109/CVPR52734.2025.02761 conf/cvpr/2025 db/conf/cvpr/cvpr2025.html#0001ZHHYZCJ0Z025