Viewpoint Recommendation for Point Cloud Labeling through Interaction Cost Modeling

TL;DR

This paper introduces a viewpoint recommendation system for 3D point cloud labeling that leverages interaction cost modeling to significantly reduce annotation time for semantic segmentation tasks.

Contribution

It adapts Fitts' law to model interaction costs and recommends optimal viewpoints, improving labeling efficiency in a new data labeling system.

Findings

Reduced labeling time in ablation studies

Effective viewpoint recommendations compared to previous methods

System supports efficient semantic segmentation annotation

Abstract

Semantic segmentation of 3D point clouds is important for many applications, such as autonomous driving. To train semantic segmentation models, labeled point cloud segmentation datasets are essential. Meanwhile, point cloud labeling is time-consuming for annotators, which typically involves tuning the camera viewpoint and selecting points by lasso. To reduce the time cost of point cloud labeling, we propose a viewpoint recommendation approach to reduce annotators' labeling time costs. We adapt Fitts' law to model the time cost of lasso selection in point clouds. Using the modeled time cost, the viewpoint that minimizes the lasso selection time cost is recommended to the annotator. We build a data labeling system for semantic segmentation of 3D point clouds that integrates our viewpoint recommendation approach. The system enables users to navigate to recommended viewpoints for efficient annotation. Through an ablation study, we observed that our approach effectively reduced the data labeling time cost. We also qualitatively compare our approach with previous viewpoint selection approaches on different datasets.