Progressive Structure from Motion

TL;DR

This paper introduces a novel progressive Structure from Motion pipeline that incrementally reconstructs 3D models from images as they become available, overcoming limitations of existing incremental and global methods.

Contribution

It presents a new reconstruction pipeline capable of delivering intermediate results, recovering from early failures, and avoiding binding decisions, unlike traditional batch or incremental approaches.

Findings

Successfully reconstructs 3D models progressively from partial data

Outperforms existing methods on challenging datasets with symmetric structures

Maintains robustness and accuracy comparable to state-of-the-art pipelines

Abstract

Structure from Motion or the sparse 3D reconstruction out of individual photos is a long studied topic in computer vision. Yet none of the existing reconstruction pipelines fully addresses a progressive scenario where images are only getting available during the reconstruction process and intermediate results are delivered to the user. Incremental pipelines are capable of growing a 3D model but often get stuck in local minima due to wrong (binding) decisions taken based on incomplete information. Global pipelines on the other hand need the access to the complete viewgraph and are not capable of delivering intermediate results. In this paper we propose a new reconstruction pipeline working in a progressive manner rather than in a batch processing scheme. The pipeline is able to recover from failed reconstructions in early stages, avoids to take binding decisions, delivers a progressive output and yet maintains the capabilities of existing pipelines. We demonstrate and evaluate our method on diverse challenging public and dedicated datasets including those with highly symmetric structures and compare to the state of the art.