CF-PRNet: Coarse-to-Fine Prototype Refining Network for Point Cloud Completion and Reconstruction
Abstract
In modern agriculture, precise monitoring of plants and fruits is crucial for tasks such as high-throughput phenotyping and automated harvesting. This paper addresses the challenge of reconstructing accurate 3D shapes of fruits from partial views, which is common in agricultural settings. We introduce CF-PRNet, a coarse-to-fine prototype refining network, leverages high-resolution 3D data during the training phase but requires only a single RGB-D image for real-time inference. Our approach begins by extracting the incomplete point cloud data that constructed from a partial view of a fruit with a series of convolutional blocks. The extracted features inform the generation of scaling vectors that refine two sequentially constructed 3D mesh prototypes - one coarse and one fine-grained. This progressive refinement facilitates the detailed completion of the final point clouds, achieving detailed and accurate reconstructions. CF-PRNet demonstrates excellent performance metrics with a Chamfer Distance of 3.78, an F1 Score of 66.76%, a Precision of 56.56%, and a Recall of 85.31%, and win the first place in the Shape Completion and Reconstruction of Sweet Peppers Challenge.
Cite
@article{arxiv.2409.08443,
title = {CF-PRNet: Coarse-to-Fine Prototype Refining Network for Point Cloud Completion and Reconstruction},
author = {Zhi Chen and Tianqi Wei and Zecheng Zhao and Jia Syuen Lim and Yadan Luo and Hu Zhang and Xin Yu and Scott Chapman and Zi Huang},
journal= {arXiv preprint arXiv:2409.08443},
year = {2024}
}
Comments
Technical Report of the 1st place solution to CVPPA@ECCV2024: Shape Completion and Reconstruction of Sweet Peppers Challenge