“SCENEVERSE: Scaling 3D Vision-Language Learning for Grounded Scene Understanding” 项目主页:https://scene-verse.github.io 论文地址:https://arxiv.org/pdf/2...
2024-02-19 619

“GenZI: Zero-Shot 3D Human-Scene Interaction Generation”     给定任意 3D 场景,GenZI 利用视觉语言模型(VLM)的强大能力,可以根据简...
2023-12-19 521
显示验证码