谢赛宁发布 Cambrian-P：以姿态为最小充分 3D 信号
📸latest in our cambrian series: cambrian-p, p for pose.
📸cambrian 系列最新成果：cambrian-p，p 代表 pose。 我认为 pose 很可能是我们需要的、用于稳健视频多模态模型的最小充分 3D 信号（而且它很容易获取！）——联合建模帧与 pose 能把图像序列转化为全局有根基的结构。
查看原帖Camera pose matters for video understanding! Today's MLLMs excel at recognizing activities, but still struggle with the underlying space and ego/object dynamics in video. We trace this gap to a missing piece: camera pose. Introducing Cambrian-P: a multimodal LLM natively grounded in camera pose. (1/n)
正文
当前显示原文，中文全文译文尚未就绪。
📸latest in our cambrian series: cambrian-p, p for pose. i think pose is probably the minimal sufficient 3d signal (and it’s easy to get!) that we need for robust video multimodal models -- jointly modeling frames and pose turns image sequences into a globally grounded structure.