SemanticPaint: A Framework for the Interactive Segmentation of 3D Scenes

TL;DR

SemanticPaint is a real-time system that enables interactive segmentation and labeling of 3D scenes using user input, machine learning, and geometric reconstruction, facilitating efficient scene understanding and annotation.

Contribution

It introduces an open-source, real-time framework combining interactive segmentation, user input, and online learning for 3D scene annotation.

Findings

Real-time 3D scene segmentation and labeling

User interaction improves segmentation accuracy

System operates efficiently in live environments

Abstract

We present an open-source, real-time implementation of SemanticPaint, a system for geometric reconstruction, object-class segmentation and learning of 3D scenes. Using our system, a user can walk into a room wearing a depth camera and a virtual reality headset, and both densely reconstruct the 3D scene and interactively segment the environment into object classes such as 'chair', 'floor' and 'table'. The user interacts physically with the real-world scene, touching objects and using voice commands to assign them appropriate labels. These user-generated labels are leveraged by an online random forest-based machine learning algorithm, which is used to predict labels for previously unseen parts of the scene. The entire pipeline runs in real time, and the user stays 'in the loop' throughout the process, receiving immediate feedback about the progress of the labelling and interacting with the scene as necessary to refine the predicted segmentation.