Distributed bundle adjustment with block-based sparse matrix compression for super large scale datasets

TL;DR

This paper introduces a distributed bundle adjustment method using exact Levenberg-Marquardt algorithm and block-based sparse matrix compression, enabling scalable and memory-efficient processing of extremely large datasets in a distributed system.

Contribution

It presents a novel distributed bundle adjustment approach with exact LM and block-based sparse matrix compression for super large-scale datasets, outperforming existing approximate methods.

Findings

Efficient memory usage demonstrated on large datasets

Scalability to datasets with over 10 million images

Parallel LM-based bundle adjustment achieved on real distributed systems

Abstract

We propose a distributed bundle adjustment (DBA) method using the exact Levenberg-Marquardt (LM) algorithm for super large-scale datasets. Most of the existing methods partition the global map to small ones and conduct bundle adjustment in the submaps. In order to fit the parallel framework, they use approximate solutions instead of the LM algorithm. However, those methods often give sub-optimal results. Different from them, we utilize the exact LM algorithm to conduct global bundle adjustment where the formation of the reduced camera system (RCS) is actually parallelized and executed in a distributed way. To store the large RCS, we compress it with a block-based sparse matrix compression format (BSMC), which fully exploits its block feature. The BSMC format also enables the distributed storage and updating of the global RCS. The proposed method is extensively evaluated and compared with the state-of-the-art pipelines using both synthetic and real datasets. Preliminary results demonstrate the efficient memory usage and vast scalability of the proposed method compared with the baselines. For the first time, we conducted parallel bundle adjustment using LM algorithm on a real datasets with 1.18 million images and a synthetic dataset with 10 million images (about 500 times that of the state-of-the-art LM-based BA) on a distributed computing system.