FBINeRF: Feature-Based Integrated Recurrent Network for Pinhole and Fisheye Neural Radiance Fields

TL;DR

FBINeRF introduces a feature-based recurrent network with adaptive bundle adjustment to improve 3D scene reconstruction from both pinhole and fisheye images, addressing distortions and depth initialization issues for higher fidelity results.

Contribution

The paper presents a novel neural network architecture that effectively handles radial distortions and depth initialization problems in NeRF-based scene reconstruction.

Findings

High-fidelity 3D reconstructions for pinhole and fisheye images.

Effective handling of radial distortions with adaptive bundle adjustment.

Improved depth initialization leading to better convergence.

Abstract

Previous studies aiming to optimize and bundle-adjust camera poses using Neural Radiance Fields (NeRFs), such as BARF and DBARF, have demonstrated impressive capabilities in 3D scene reconstruction. However, these approaches have been designed for pinhole-camera pose optimization and do not perform well under radial image distortions such as those in fisheye cameras. Furthermore, inaccurate depth initialization in DBARF results in erroneous geometric information affecting the overall convergence and quality of results. In this paper, we propose adaptive GRUs with a flexible bundle-adjustment method adapted to radial distortions and incorporate feature-based recurrent neural networks to generate continuous novel views from fisheye datasets. Other NeRF methods for fisheye images, such as SCNeRF and OMNI-NeRF, use projected ray distance loss for distorted pose refinement, causing severe artifacts, long rendering time, and are difficult to use in downstream tasks, where the dense voxel representation generated by a NeRF method needs to be converted into a mesh representation. We also address depth initialization issues by adding MiDaS-based depth priors for pinhole images. Through extensive experiments, we demonstrate the generalization capacity of FBINeRF and show high-fidelity results for both pinhole-camera and fisheye-camera NeRFs.