Blending Distributed NeRFs with Tri-stage Robust Pose Optimization

TL;DR

This paper introduces a tri-stage pose optimization method for distributed NeRFs, significantly improving registration accuracy and rendering quality in large urban environments by addressing aliasing and pose errors.

Contribution

It proposes a novel three-stage pose optimization framework combining bundle adjustment, Frame2Model, and Model2Model techniques for robust distributed NeRF registration.

Findings

Achieves more accurate pose estimation in distributed NeRFs

Reduces aliasing artifacts during NeRF blending

Demonstrates superior performance in real-world and simulated scenarios

Abstract

Due to the limited model capacity, leveraging distributed Neural Radiance Fields (NeRFs) for modeling extensive urban environments has become a necessity. However, current distributed NeRF registration approaches encounter aliasing artifacts, arising from discrepancies in rendering resolutions and suboptimal pose precision. These factors collectively deteriorate the fidelity of pose estimation within NeRF frameworks, resulting in occlusion artifacts during the NeRF blending stage. In this paper, we present a distributed NeRF system with tri-stage pose optimization. In the first stage, precise poses of images are achieved by bundle adjusting Mip-NeRF 360 with a coarse-to-fine strategy. In the second stage, we incorporate the inverting Mip-NeRF 360, coupled with the truncated dynamic low-pass filter, to enable the achievement of robust and precise poses, termed Frame2Model optimization. On top of this, we obtain a coarse transformation between NeRFs in different coordinate systems. In the third stage, we fine-tune the transformation between NeRFs by Model2Model pose optimization. After obtaining precise transformation parameters, we proceed to implement NeRF blending, showcasing superior performance metrics in both real-world and simulation scenarios. Codes and data will be publicly available at https://github.com/boilcy/Distributed-NeRF.