ML Anthology

Proposal-Free LiDAR Panoptic Segmentation with Pillar-Level Affinity

Qi Chen, Sourabh Vora
CVPRW 2022 pp. 4528-4535
doi:10.1109/CVPRW56347.2022.00499 /cvprw/2022/chen2022cvprw-proposalfree/

Abstract

We propose a simple yet effective proposal-free architecture for lidar panoptic segmentation. We jointly optimize both semantic segmentation and class-agnostic instance classification in a single network using a pillar-based bird’s-eye view representation. The instance classification head learns pairwise affinity between pillars to determine whether the pillars belong to the same instance or not. We further propose a local clustering algorithm to propagate instance ids by merging semantic segmentation and affinity predictions. Our experiments on nuScenes dataset show that our approach outperforms previous proposal-free methods and is comparable to proposal-based methods which requires extra annotation from object detection.

PDF CVPRW Semantic Scholar

Cite

Text

Chen and Vora. "Proposal-Free LiDAR Panoptic Segmentation with Pillar-Level Affinity." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2022. doi:10.1109/CVPRW56347.2022.00499

Markdown

[Chen and Vora. "Proposal-Free LiDAR Panoptic Segmentation with Pillar-Level Affinity." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2022.](https://mlanthology.org/cvprw/2022/chen2022cvprw-proposalfree/) doi:10.1109/CVPRW56347.2022.00499

BibTeX

@inproceedings{chen2022cvprw-proposalfree,
  title     = {{Proposal-Free LiDAR Panoptic Segmentation with Pillar-Level Affinity}},
  author    = {Chen, Qi and Vora, Sourabh},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2022},
  pages     = {4528-4535},
  doi       = {10.1109/CVPRW56347.2022.00499},
  url       = {https://mlanthology.org/cvprw/2022/chen2022cvprw-proposalfree/}
}