Plant 3D reconstruction using optical imaging often suffers from incomplete point clouds due to viewpoint occlusion and sensor limitations. This incompleteness hinders accurate structural representation and subsequent feature extraction for plant analysis. To address these challenges, we propose a Multi-Scale Dual-Discriminator Generative Adversarial Network (MSDDG) for plant point cloud completion. A multi-scale point cloud generator (MSPG) that integrates local and global features from raw incomplete point clouds is used for MSDDG to reconstruct complete shapes. The dual-discriminators-a multi-view projected silhouette discriminator and a spatial distance discriminator-are designed to ensure geometric realism and spatial plausibility from multiple perspectives. To train MSDDG, we created the Plant4L dataset containing four plant species (sunflower, pumpkin, luffa, and eggplant) with high-quality 3D models augmented via 3D thin plate spline transformations and virtual occlusion simulation to generate incomplete point clouds and multi-view silhouettes. Experimental results on Plant4L demonstrate that MSDDG achieves superior completion performance, with Chamfer Distance (CD), Hausdorff Distance (HD), and Uniformity Chamfer Distance (UCD) all below 0.41. Comparative evaluations confirm MSDDG's superiority over previous point cloud completion methods. The application of MSDDG for 3D reconstruction from single view further validate its effectiveness in restoring occluded plant structures.
Why it matches plant phenotyping methods植物の不完全点群を補完して3D構造を再構成する手法を開発し、植物データセット上で比較評価・検証しており、表現型取得ワークフローが中心です。
abstractwe propose a Multi-Scale Dual-Discriminator Generative Adversarial Network (MSDDG) for plant point cloud completion.
Reproduction assets foundThe paper's data availability statement explicitly states that the source code and datasets (including the Plant4L point cloud completion dataset) are publicly available at the authors' GitHub repository.Code · publicThe source code and datasets used in this study are publicly available at https://github.com/Amuro-Aznable/MSCGPCN.git .Open asset ↗https://github.com/Amuro-Aznable/MSCGPCN.git · MSCGPCNlines:415-421Code / dataset availability confirmedCrossref · Europe PMC · checked 6 Sept 2026
The Ash Gourd dataset is valuable since it was collected from the diverse regions within the district of Dhaka in Bangladesh. This dataset represents one of the first attempts to document, elicit, and categorize the health conditions of Ash Gourd (Benincasa hispida) plants in Bangladesh based on healthy samples, aphid plurality, downy mildew, leaf curl, and leaf miner-infested categories. Ash Gourd is one of the region's most important vegetables because of its nutritional and economic value; thus, it is essential to know diseases' manifestation in the improvement of agricultural productivity. The Ash Gourd dataset contains 2676 images, structured into the five categories of Healthy, Aphid, Downy Mildew, Leaf Curl, and Leaf Miner. All images in all categories are raw which can be used flexibly according to the needs of analysis and model training. Concretely, the Healthy class consists of 803 images, while the four other classes contain 1,873 images. This structured way of collecting data will, in turn, enable deeper analysis and help construct machine learning models for disease classification, hence providing worthy insights into Ash Gourd plant health.
Why it matches plant phenotyping methodsアッシュゴード葉の画像データセットを構築し、植物の健康状態・病徴カテゴリを分類するための再利用可能なデータ資源を提供しており、植物病害状態の画像ベース表現型解析が中心です。
abstractThe Ash Gourd dataset contains 2676 images, structured into the five categories of Healthy, Aphid, Downy Mildew, Leaf Curl, and Leaf Miner.
Reproduction assets foundThe paper's own ash gourd leaf image dataset (2676 images, five classes) is publicly deposited on Mendeley Data with an explicit direct URL and DOI, matching the paper's phenotyping measurements.Dataset · publicRepository name: Mendeley Data
Data identification number: 10.17632/zj4th6xvdp.2
Direct URL to data:https://data.mendeley.com/datasets/zj4th6xvdp/2Open asset ↗Mendeley Data · 10.17632/zj4th6xvdp.2html-lines:1-98Code / dataset availability confirmedEurope PMC · Crossref · checked 7 Sept 2026
Introduction Recently, plant disease detection and diagnosis procedures have become a primary agricultural concern. Early detection of plant diseases enables farmers to take preventative action, stopping the disease's transmission to other plant sections. Plant diseases are a severe hazard to food safety, but because the essential infrastructure is missing in various places around the globe, quick disease diagnosis is still difficult. The plant may experience a variety of attacks, from minor damage to total devastation, depending on how severe the infections are. Thus, early detection of plant diseases is necessary to optimize output to prevent such destruction. The physical examination of plant diseases produced low accuracy, required a lot of time, and could not accurately anticipate the plant disease. Creating an automated method capable of accurately classifying to deal with these issues is vital. Method This research proposes an efficient, novel, and lightweight DeepPlantNet deep learning (DL)-based architecture for predicting and categorizing plant leaf diseases. The proposed DeepPlantNet model comprises 28 learned layers, i.e., 25 convolutional layers (ConV) and three fully connected (FC) layers. The framework employed Leaky RelU (LReLU), batch normalization (BN), fire modules, and a mix of 3×3 and 1×1 filters, making it a novel plant disease classification framework. The Proposed DeepPlantNet model can categorize plant disease images into many classifications. Results The proposed approach categorizes the plant diseases into the following ten groups: Apple_Black_rot (ABR), Cherry_(including_sour)_Powdery_mildew (CPM), Grape_Leaf_blight_(Isariopsis_Leaf_Spot) (GLB), Peach_Bacterial_spot (PBS), Pepper_bell_Bacterial_spot (PBBS), Potato_Early_blight (PEB), Squash_Powdery_mildew (SPM), Strawberry_Leaf_scorch (SLS), bacterial tomato spot (TBS), and maize common rust (MCR). The proposed framework achieved an average accuracy of 98.49 and 99.85in the case of eight-class and three-class classification schemes, respectively. Discussion The experimental findings demonstrated the DeepPlantNet model's superiority to the alternatives. The proposed technique can reduce financial and agricultural output losses by quickly and effectively assisting professionals and farmers in identifying plant leaf diseases.
Why it matches plant phenotyping methods葉画像から植物病害状態を分類する深層学習手法を開発しており、植物の病徴・病害状態の取得と推定が研究の中心であるため。
abstractThis research proposes an efficient, novel, and lightweight DeepPlantNet deep learning (DL)-based architecture for predicting and categorizing plant leaf diseases.
Reproduction assets foundThe paper's plant leaf disease classification experiments are built entirely on two public Kaggle image datasets explicitly cited by the authors: the PlantVillage Dataset (eight-class experiment) and the Plant Disease Prediction Dataset (three-class experiment). No author code, trained model, or supplementary deposit (Dataset · publicWe verified the effectiveness and robustness of the DeepPlantNet model by using images from the publicly available Kaggle “PlantVillage Dataset” dataset ( Dataset : https://www.kaggle.com/datasets/abdallahalidev/plantvillage-dataset ).Open asset ↗Kaggle · abdallahalidev/plantvillage-datasetlines:355-366Dataset · publicWe validated our model using another common, publicly accessible Kaggle dataset, “Plant Disease Prediction Dataset,” to assess and estimate the generalizability and performance of the DeepPlantNet model ( Dataset : https://www.kaggle.com/datasets/shuvranshu/plant-disease-prediction-dataset ).Open asset ↗Kaggle · shuvranshu/plant-disease-prediction-datasetlines:729-756