arXiv cs.AI· Pieter M. Blok, Haozhou Wang, Hyun Kwon Suh, Peicheng Wang, James Burridge, Wei Guo·· 11 小时前AI 评分22
PointRAFT：用 3D 深度学习从部分点云高通量预测马铃薯块茎重量
PointRAFT: 3D deep learning for high-throughput prediction of potato tuber weight from partial point clouds
AI 导读
PointRAFT 是一种点云回归网络，通过专用的高度嵌入引入相机与传送带固定距离提供的几何线索，从自遮挡导致的不完整点云中估计马铃薯块茎重量。在 859 个块茎、26,688 个点云（4 个品种、3 个生长季）上训练后，其在 5,254 个点云的测试集上取得 MAE 11.7 g、RMSE 17.1 g，优于六个无高度嵌入的点云回归网络。
正文 · 原文
Abstract:Key phenotypic traits, such as crop size, volume, and weight, can be estimated non-destructively from point clouds. In practice, however, point clouds of crops are typically incomplete due to self-occlusion, leading to systematic errors when estimating these traits. To overcome this limitation, crop traits can be inferred directly from incomplete point clouds using deep learning-based regression networks. These networks, however, may perform suboptimally, because their predictions do not incorporate prior geometric knowledge of the crop. Such geometric knowledge is often available in structured settings, such as on a potato harvester, where the fixed distance between the camera and the conveyor belt allows tuber height to be derived from the point cloud. To exploit this geometric cue, we introduce PointRAFT, a high-throughput point cloud regression network that incorporates object height through a dedicated height embedding. We hypothesized that this height embedding improves tuber weight estimation from partial point clouds. To test this hypothesis, we collected 26,688 point clouds of 859 potato tubers on an operational harvester, spanning four cultivars and three growing seasons. On a test set of 5,254 point clouds representing 172 tubers, PointRAFT achieved a mean absolute error (MAE) of 11.7 g and a root mean squared error (RMSE) of 17.1 g, outperforming six point cloud regression networks without a height embedding. Requiring only 6.3 ms per point cloud for preprocessing and inference, PointRAFT is fast enough for high-throughput weight estimation on a commercial potato harvester. Beyond potato weight estimation, PointRAFT provides a versatile regression network applicable to a wide range of 3D phenotyping and robotic perception tasks. The code, network weights, and a subset of the dataset are publicly available at this https URL.
| Comments: | 36 pages, 6 figures, 4 tables |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2512.24193 [cs.CV] |
| (or arXiv:2512.24193v2 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2512.24193 arXiv-issued DOI via DataCite |
Submission history
From: Pieter Blok [view email]
[v1]
Tue, 30 Dec 2025 12:52:20 UTC (14,672 KB)
[v2]
Wed, 4 Nov 2026 13:12:58 UTC (15,051 KB)
来源：arXiv cs.AI · arxiv.org