论文标题
nope-nerf：优化神经辐射场，没有姿势
NoPe-NeRF: Optimising Neural Radiance Field with No Pose Prior
论文作者
论文摘要
训练没有预先计算的相机姿势的神经辐射场（NERF）具有挑战性。在这个方向上的最新进展表明，在前面的场景中共同优化NERF和相机摆姿势的可能性。但是，这些方法在戏剧性的相机运动过程中仍然面临困难。我们通过纳入不贴发的单眼深度先验来解决这个具有挑战性的问题。这些先验是通过在训练过程中校正量表和移位参数而生成的，然后我们就可以通过它们来约束连续帧之间的相对姿势。使用我们提出的新型损失功能来实现此约束。在现实世界中室内和室外场景的实验表明，我们的方法可以在新颖的视图方面处理具有挑战性的摄像头轨迹，并优于现有方法，从而使质量和姿势估计准确性。我们的项目页面是https://nope-nerf.active.vision。
Training a Neural Radiance Field (NeRF) without pre-computed camera poses is challenging. Recent advances in this direction demonstrate the possibility of jointly optimising a NeRF and camera poses in forward-facing scenes. However, these methods still face difficulties during dramatic camera movement. We tackle this challenging problem by incorporating undistorted monocular depth priors. These priors are generated by correcting scale and shift parameters during training, with which we are then able to constrain the relative poses between consecutive frames. This constraint is achieved using our proposed novel loss functions. Experiments on real-world indoor and outdoor scenes show that our method can handle challenging camera trajectories and outperforms existing methods in terms of novel view rendering quality and pose estimation accuracy. Our project page is https://nope-nerf.active.vision.
