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.

翻译：在无预计算相机位姿的情况下训练神经辐射场（NeRF）极具挑战性。近期相关研究展示了在前向场景中联合优化NeRF与相机位姿的可能性，但此类方法在处理大幅度相机运动时仍存在困难。我们通过引入无畸变单目深度先验来解决这一难题：利用训练过程中校正尺度与偏移参数生成的深度先验，约束连续帧间的相对位姿，并据此提出新型损失函数。在真实室内外场景上的实验表明，本方法能处理具有挑战性的相机轨迹，在新视角渲染质量与位姿估计精度上均优于现有方法。项目页面：https://nope-nerf.active.vision。