PlantPCC: Dual Sampling and Multi-level Geometry-aware Contrastive Regularization for Plant Point Cloud Completion

Plant point cloud completion is essential for tasks like segmentation and surface reconstruction in plant phenotyping. Unlike the relatively simpler Computer-Aided Design models found in datasets like ShapeNet, plant point clouds are characterized by their rich geometric shapes and intricate edge features, making the task of completion significantly more challenging. In response to this, we propose a learnable uniform-edge dual sampling feature extractor that efficiently captures complex geometric features in plant point clouds by ensuring comprehensive coverage of overall structures while focusing on edge regions with critical geometric details. Additionally, we propose a multi-level geometry-aware contrastive regularization method to improve the alignment between the predicted point clouds and the missing regions, enhancing their distributional similarity to the ground truth. Experiments on the PlantPCC dataset show our model outperforms state-of-the-art methods, improving Chamfer Distance by 6.4% over the second-best model. Relevant datasets and codes are available at https://github.com/liqingque/PlantPCC.