Unsupervised Point Cloud Pre-Training via Contrasting and Clustering

Researchers propose ConClu, an unsupervised pre-training framework for point clouds that combines contrasting and clustering techniques to learn discriminative representations without labeled data. The method outperforms state-of-the-art approaches on multiple downstream tasks, addressing the challenge of expensive point cloud annotation.

• →ConClu framework integrates contrasting and clustering for unsupervised point cloud pre-training without requiring labeled data.
• →The contrasting objective maximizes similarity between augmented views of the same point cloud.
• →The clustering objective partitions data and enforces consistency between cluster assignments across augmentations.
• →Experimental results demonstrate superior performance compared to existing state-of-the-art methods.
• →The approach addresses the time-consuming and often infeasible problem of large-scale point cloud annotation.