English

ViewPCL: a point cloud based active learning method for multi-view segmentation

Computer Vision and Pattern Recognition 2025-06-17 v1

Abstract

We propose a novel active learning framework for multi-view semantic segmentation. This framework relies on a new score that measures the discrepancy between point cloud distributions generated from the extra geometrical information derived from the model's prediction across different views. Our approach results in a data efficient and explainable active learning method. The source code is available at https://github.com/chilai235/viewpclAL.

Keywords

Cite

@article{arxiv.2506.13043,
  title  = {ViewPCL: a point cloud based active learning method for multi-view segmentation},
  author = {Christian Hilaire and Sima Didari},
  journal= {arXiv preprint arXiv:2506.13043},
  year   = {2025}
}
R2 v1 2026-07-01T03:18:49.111Z