Joint Semantic Segmentation using representations of LiDAR point clouds and camera images

Yue Wu, Jiaming Liu, Maoguo Gong, Qiguang Miao, Wenping Ma, Cai Xu

Abstract

Highlights•We revisit the key factor of LiDAR-camera fusion, namely the soft joint mechanism.•We develop an attention-based multimodal fusion in point cloud segmentation.•We build multi-scale pairwise inputs and interact using the dual-stream transformer.•We propose unimodal data augmentation and cross-modal contrastive learning.
BibTeX
@article{wu2024joint,
  author = {Yue Wu and Jiaming Liu and Maoguo Gong and Qiguang Miao and Wenping Ma and Cai Xu},
  title = {{Joint Semantic Segmentation using representations of LiDAR point clouds and camera images}},
  journal = {Information Fusion},
  year = {2024},
  url = {https://openreview.net/forum?id=tJkQWfIlZA},
}

Loading related content...

Figure