no code implementations • 11 Mar 2024 • Peng Zhang, Ting Wu, Jinsheng Sun, Weiqing Li, Zhiyong Su
This paper concentrates on an unexplored yet meaningful task, i. e., interactive point cloud semantic segmentation, which assigns high-quality semantic labels to all points in a scene with user corrective clicks.
no code implementations • 2 Nov 2022 • Zhuheng Lu, Yuewei Dai, Weiqing Li, Zhiyong Su
To address the issues, we propose a simple but efficient augmentation fusion contrastive learning framework to combine data augmentations in Euclidean space and feature augmentations in feature space.
no code implementations • 2 Nov 2022 • Zhuheng Lu, Peng Zhang, Yuewei Dai, Weiqing Li, Zhiyong Su
Secondly, the WHCN takes the hypergraph as input and learns to predict high-precision point-level pseudo labels by label propagation.
no code implementations • 2 Nov 2022 • Peng Zhang, Ruoyin Xie, Jinsheng Sun, Weiqing Li, Zhiyong Su
Given an input point cloud of arbitrary size, we first perform a task-agnostic pre-sampling on the input point cloud to a specified sample size.