Reconstructing Small 3D Objects in front of a Textured Background

TL;DR

This paper introduces a novel method for complete 3D reconstruction of small objects in front of textured backgrounds, leveraging multibody structure from motion to improve accuracy and practicality.

Contribution

It presents a specialized multibody structure from motion approach for two objects, integrating local segmentation and merging techniques into the COLMAP pipeline.

Findings

Outperforms state-of-the-art methods in reconstructing objects from all sides.

Effective segmentation and merging improve reconstruction accuracy.

Practical advantages demonstrated on real artifact data.

Abstract

We present a technique for a complete 3D reconstruction of small objects moving in front of a textured background. It is a particular variation of multibody structure from motion, which specializes to two objects only. The scene is captured in several static configurations between which the relative pose of the two objects may change. We reconstruct every static configuration individually and segment the points locally by finding multiple poses of cameras that capture the scene's other configurations. Then, the local segmentation results are combined, and the reconstructions are merged into the resulting model of the scene. In experiments with real artifacts, we show that our approach has practical advantages when reconstructing 3D objects from all sides. In this setting, our method outperforms the state-of-the-art. We integrate our method into the state of the art 3D reconstruction pipeline COLMAP.