Structure-aware completion of plant 3D LiDAR point clouds via a multi-resolution GAN-inversion network

Abstract

Introduction Three-dimensional (3D) point clouds acquired by LiDAR are fundamental for applications such as autonomous navigation, mobile robotics, infrastructure inspection, and cultural-heritage documentation. However, environmental disturbances and sensor limitations often yield incomplete or noisy point clouds, degrading downstream performance. This study addresses robust, high-fidelity point cloud completion under such practical conditions. Methods We propose an unsupervised deep learning framework, Multi-Resolution Completion Net (MRC-Net), which builds on ShapeInversion by integrating a Generative Adversarial Network (GAN) inversion strategy with multi-resolution principles. The architecture comprises an encoder for feature extraction, a generator for completion, and a discriminator to assess geometric integrity and detail. Two key designs enable strong performance without supervision: (i) a multi-resolution degradation mechanism that guides reconstruction across coarse-to-fine scales, and (ii) a multi-scale discriminator that captures both global structure and local details. Results Extensive experiments on multiple datasets demonstrate that MRC-Net achieves accuracy comparable to leading supervised approaches. On virtual datasets (e.g., CRN), MRC-Net attains an average Chamfer Distance (CD) of 8.0 and an F1 score of 91.3. On a custom dataset targeting agricultural scenarios, the model preserves object integrity across varying complexity: for regular cartons, it achieves CD 3.3 and F1 97.3; for structurally complex simulated plants, it maintains overall shape while delivering average CD 8.6 and F1 88.1. Discussion These results indicate that MRC-Net advances unsupervised point cloud completion by balancing global shape consistency with fine-grained detail. The method provides a reliable data foundation for downstream tasks—including autonomous navigation, high-precision 3D modeling, and agricultural robotics—thereby contributing to improved data quality in precision-agriculture and related domains.

Plant phenotyping relevance

植物3D LiDAR点群の欠損補完を主題とする手法開発であり、植物形状の再構成性能を実験的に検証しているため、植物形態フェノタイピングに再利用可能な中心的手法研究と判断する。

Code and data availability

The supplied blocks describe MRC-Net, a point cloud completion method using CRN/ShapeNet datasets and a custom agricultural LiDAR dataset, but contain no data availability statement, no author code/model deposit, and no public URL for any paper-specific asset. The only URL present is the CC BY license notice.

No evidence-backed public reproduction asset is currently recorded.