NoPe-NeRF: Optimising Neural Radiance Field with No Pose Prior

By Wenjing Bian, Zirui Wang, Kejie Li, Jiawang Bian, Victor Adrian Prisacariu. Computer Vision and Pattern Recognition, 2022

363 citations recorded by the source corpus.

Training a Neural Radiance Field (NeRF) without precomputed 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.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/9a1646e96ae3bda9f528ca747a3c7f591735f2c0

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Xin Ning
2. Xiao Bai
3. Lin Gu
4. Jiahe Li
5. Jun Zhou
6. Jin Zheng
7. Jiawei Zhang

Citations in the corpus

• DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalization (2024, methodology): “In this work, we use the pre-trained DPT [29, 30] estimator to predict the depth map, which has been widely used in many NeRF-based works [4, 10, 42, 48].”
• DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes (2023, neutral): “We also find that our baseline method, 3DGS [4], fails in modeling the detail areas, producing unpleasant artifacts, blurring, and unnatural colors.”