RayDer: Scalable Self-Supervised Novel View Synthesis from Real-World Video 事件

RayDer: Scalable Self-Supervised Novel View Synthesis from Real-World Video arXiv:2605.31535v1 Announce Type: new Abstract: Self-supervised novel view synthesis (NVS) remains challenging to scale, despite the abundance of video data, largely due to the brittleness of training on realistic videos and the hard-to-predict scaling behavior of multi-network system designs. We introduce RayDer, a unified, feed-forward transformer that consolidates camera estimation, scene reconstruction, and renderin