3DVLA: Enhancing Vision-Language-Action Models via 3D Spatial and Instance Understanding 文章

ArXiv CS.CV2026-05-29NEWSen作者: Zhongyu Xia, Yousen Tang, Bingqing Wei, Yongtao Wang
查看原文 →
关系图谱

3DVLA: Enhancing Vision-Language-Action Models via 3D Spatial and Instance Understanding · 相关技术

相关技术

vision-language-action modelsVLM priors3D perception3D perception methods3D instance understandingmulti-view consistency3D scene understandingVLM