Pic@Point: Cross-Modal Learning by Local and Global Point-Picture Correspondence

Self-supervised pre-training has achieved remarkable success in NLP and 2D vision. However, these advances have yet to translate to 3D data. Techniques like masked reconstruction face inherent challenges on unstructured point clouds, while many contrastive learning tasks lack in complexity and informative value. In this paper, we present Pic@Point, an effective contrastive learning method based on structural 2D-3D correspondences. We leverage image cues rich in semantic and contextual knowledge to provide a guiding signal for point cloud representations at various abstraction levels. Our lightweight approach outperforms state-of-the-art pre-training methods on several 3D benchmarks.