Hugging Face Daily Papers· NVIDIA, Sérgio Agostinho, Maximilian Apodaca, Emmanuel Attia, Guillem Braso, George Dong, Ilya Fedorov, Michele Fenzi, Gang Huang, Jiahui Huang, Shengyu Huang, Bingxin Ke, Laura Leal-Taixé, Kuan-Ting Lee, Mingxuan Liu, Tian Liu, Tim Meinhardt, Aljoša Ošep, Naveen Kumar Rai, Kefei Ren, Cristiano Saltori, Keqiang Wu, Ning Xu, Fei Xue, Jin-Bey Yu, Lei Zhang, Qunjie Zhou·· 2 天前AI 评分49
NVIDIA 发布 Foundation4D：面向自动驾驶的统一感知与重建模型
Foundation4D: Towards a unified perception and reconstruction model for autonomous vehicles
AI 导读
NVIDIA 推出 Foundation4D，一个基于多相机驾驶视频、前馈式统一模型，可完成几何估计、3D 检测、语义占据和 Gaussian 重建。其共享骨干网络采用分解式时空注意力，并配套发布含 1,253 段驾驶片段密集深度与语义占据标注的 PAI-Foundation4D 基准。