NoPe-NeRF++: Local-to-Global Optimization of NeRF with No Pose Prior

TL;DR

NoPe-NeRF++ presents a combined local-to-global optimization approach for training NeRF without pose priors, improving pose accuracy and view synthesis quality through feature matching, joint optimization, and bundle adjustment.

Contribution

It introduces the first method to seamlessly integrate local and global cues for NeRF training without pose priors, enhancing robustness and accuracy.

Findings

Outperforms state-of-the-art in pose estimation accuracy

Achieves superior novel view synthesis quality

Demonstrates robustness on challenging datasets

Abstract

In this paper, we introduce NoPe-NeRF++, a novel local-to-global optimization algorithm for training Neural Radiance Fields (NeRF) without requiring pose priors. Existing methods, particularly NoPe-NeRF, which focus solely on the local relationships within images, often struggle to recover accurate camera poses in complex scenarios. To overcome the challenges, our approach begins with a relative pose initialization with explicit feature matching, followed by a local joint optimization to enhance the pose estimation for training a more robust NeRF representation. This method significantly improves the quality of initial poses. Additionally, we introduce global optimization phase that incorporates geometric consistency constraints through bundle adjustment, which integrates feature trajectories to further refine poses and collectively boost the quality of NeRF. Notably, our method is the first work that seamlessly combines the local and global cues with NeRF, and outperforms state-of-the-art methods in both pose estimation accuracy and novel view synthesis. Extensive evaluations on benchmark datasets demonstrate our superior performance and robustness, even in challenging scenes, thus validating our design choices.