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

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.

References in corpus (10)

• Instant Neural Graphics Primitives with a Multiresolution Hash Encoding
• SAMURAI: Shape And Material from Unconstrained Real-world Arbitrary Image collections
• 3D Gaussian Splatting for Real-Time Radiance Field Rendering
• InfoNeRF: Ray Entropy Minimization for Few-Shot Neural Volume Rendering
• NoPe-NeRF: Optimising Neural Radiance Field with No Pose Prior
• Modeling Indirect Illumination for Inverse Rendering
• NICE-SLAM: Neural Implicit Scalable Encoding for SLAM
• Progressively Optimized Local Radiance Fields for Robust View Synthesis
• LU-NeRF: Scene and Pose Estimation by Synchronizing Local Unposed NeRFs
• TrackNeRF: Bundle Adjusting NeRF from Sparse and Noisy Views via Feature Tracks