English

Joint prototype and coefficient prediction for 3D instance segmentation

Computer Vision and Pattern Recognition 2024-07-11 v1

Abstract

3D instance segmentation is crucial for applications demanding comprehensive 3D scene understanding. In this paper, we introduce a novel method that simultaneously learns coefficients and prototypes. Employing an overcomplete sampling strategy, our method produces an overcomplete set of instance predictions, from which the optimal ones are selected through a Non-Maximum Suppression (NMS) algorithm during inference. The obtained prototypes are visualizable and interpretable. Our method demonstrates superior performance on S3DIS-blocks, consistently outperforming existing methods in mRec and mPrec. Moreover, it operates 32.9% faster than the state-of-the-art. Notably, with only 0.8% of the total inference time, our method exhibits an over 20-fold reduction in the variance of inference time compared to existing methods. These attributes render our method well-suited for practical applications requiring both rapid inference and high reliability.

Keywords

Cite

@article{arxiv.2407.06958,
  title  = {Joint prototype and coefficient prediction for 3D instance segmentation},
  author = {Remco Royen and Leon Denis and Adrian Munteanu},
  journal= {arXiv preprint arXiv:2407.06958},
  year   = {2024}
}

Comments

Published in Electronics Letters

R2 v1 2026-06-28T17:34:30.584Z