Incremental Object Database: Building 3D Models from Multiple Partial Observations

TL;DR

This paper introduces an incremental system for building 3D object databases from partial observations without prior shape knowledge, enabling real-time scene understanding and model completion.

Contribution

It presents a novel online approach that extracts, matches, and merges object segments from RGB-D data to incrementally build comprehensive 3D object models.

Findings

Successfully constructs and refines object models in real-time

Reconstructs unobserved scene parts using merged object models

Validated on public and new Tango datasets with multiple object instances

Abstract

Collecting 3D object datasets involves a large amount of manual work and is time consuming. Getting complete models of objects either requires a 3D scanner that covers all the surfaces of an object or one needs to rotate it to completely observe it. We present a system that incrementally builds a database of objects as a mobile agent traverses a scene. Our approach requires no prior knowledge of the shapes present in the scene. Object-like segments are extracted from a global segmentation map, which is built online using the input of segmented RGB-D images. These segments are stored in a database, matched among each other, and merged with other previously observed instances. This allows us to create and improve object models on the fly and to use these merged models to reconstruct also unobserved parts of the scene. The database contains each (potentially merged) object model only once, together with a set of poses where it was observed. We evaluate our pipeline with one public dataset, and on a newly created Google Tango dataset containing four indoor scenes with some of the objects appearing multiple times, both within and across scenes.