论文标题
Mononerf：从没有相机姿势的单眼视频中学习可通用的nerfs
MonoNeRF: Learning Generalizable NeRFs from Monocular Videos without Camera Pose
论文作者
论文摘要
我们提出了一个可概括的神经辐射场-Mononerf，可以在大规模的单眼视频中进行训练，该视频在静态场景中移动而没有任何深度和相机姿势的地面真相注释。 Mononerf遵循基于自动编码器的体系结构，在该体系结构中，编码器估算单眼深度和相机姿势，而解码器基于深度编码器功能构造了多层NERF表示，并使用估计的相机构建输入框架。学习是由重建错误监督的。一旦学习了模型，就可以将其应用于多个应用程序，包括深度估计，摄像头估计和单图像新视图合成。可以提供更多定性结果，网址为：https：//oasisyang.github.io/mononerf。
We propose a generalizable neural radiance fields - MonoNeRF, that can be trained on large-scale monocular videos of moving in static scenes without any ground-truth annotations of depth and camera poses. MonoNeRF follows an Autoencoder-based architecture, where the encoder estimates the monocular depth and the camera pose, and the decoder constructs a Multiplane NeRF representation based on the depth encoder feature, and renders the input frames with the estimated camera. The learning is supervised by the reconstruction error. Once the model is learned, it can be applied to multiple applications including depth estimation, camera pose estimation, and single-image novel view synthesis. More qualitative results are available at: https://oasisyang.github.io/mononerf .
