Scale Matters: Adaptive Granularity Selection for Cross-Species 3D Plant Organ Segmentation

• URL: http://arxiv.org/abs/2608.17803v2
• Date: Wed, 19 Aug 2026 09:08:46 GMT
• Title: Scale Matters: Adaptive Granularity Selection for Cross-Species 3D Plant Organ Segmentation
• Abstract summary: We propose AGS-PlantSeg, a few-shot 3D plant organ segmentation method.<n>We show that AGS-PlantSeg significantly improves cross-species generalization, achieving 88.9% average mIoU performance.<n>Despite requiring minimal data annotated, our approach is highly competitive with fully supervised, plant-specific architectures.
• Score: 2.182911602491685
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent 3D foundation models provide powerful feature representations for point cloud learning by controlling spatial granularity. However, relying on a fixed spatial granularity severely limits generalization in applications like plant phenotyping, where organ morphology and size vary substantially across species and growth stages. To address this, we propose AGS-PlantSeg, a few-shot 3D plant organ segmentation method that leverages the frozen Utonia (arXiv:2603.03283) foundation model combined with Adaptive Granularity Selection. By dynamically selecting the best granularity levels for each specific plant model, our method extracts optimized geometric features for a lightweight MLP segmentation head. Extensive experiments across PLANesT-3D (arXiv:2407.21150), Pheno4D , and Crops3D demonstrate that AGS-PlantSeg significantly improves cross-species generalization, achieving 88.9% average mIoU performance and outperforming fixed-granularity baselines by 2.5 mIoU points. Despite requiring minimal annotated data, our approach is highly competitive with fully supervised, plant-specific architectures.

Related papers

• NG-GS: NeRF-Guided 3D Gaussian Splatting Segmentation [65.34304674634713]
  We introduce NG-GS, a framework for high-quality object segmentation in 3DGS that explicitly addresses boundary discretization.<n>We show that our method achieves photorealistic state-of-the-art performance, with significant gains in boundary mIoU.
  arXiv  Detail & Related papers  (2026-04-16T07:14:07Z)
• Scalable Adaptation of 3D Geometric Foundation Models via Weak Supervision from Internet Video [76.32954467706581]
  We propose SAGE, a framework for Scalable Adaptation of GEometric foundation models from raw video streams.<n>We use a hierarchical mining pipeline to transform videos into training trajectories and hybrid supervision.<n>Experiments show that SAGE significantly enhances zero-shot generalization, reducing Chamfer Distance by 20-42% on unseen benchmarks.
  arXiv  Detail & Related papers  (2026-02-08T09:53:21Z)
• OmniPlantSeg: Species Agnostic 3D Point Cloud Organ Segmentation for High-Resolution Plant Phenotyping Across Modalities [4.770378899761483]
  It is common to use extensive pre-processing and down-sample the plant point clouds to meet hardware or neural network input size requirements.<n>We propose a simple, yet effective algorithm KDSS for sub-sampling of biological point clouds that is agnostic to sensor data and plant species.
  arXiv  Detail & Related papers  (2025-09-25T11:45:14Z)
• PlantSegNeRF: A few-shot, cross-species method for plant 3D instance point cloud reconstruction via joint-channel NeRF with multi-view image instance matching [9.176076520337755]
  We propose a novel approach called plant segmentation neural radiance fields (PlantSegNeRF)<n>PlantSegNeRF directly generates high-precision instance point clouds from multi-view RGB image sequences for a wide range of plant species.<n>Across all plant species, it achieved average improvements of 11.7%, 38.2%, 32.2% and 25.3% in mPrec, mRec, mCov, mWCov, respectively.
  arXiv  Detail & Related papers  (2025-07-01T01:59:59Z)
• On Geometry-Enhanced Parameter-Efficient Fine-Tuning for 3D Scene Segmentation [52.96632954620623]
  We introduce a novel geometry-aware PEFT module specifically designed for 3D point cloud transformers.<n>Our approach sets a new benchmark for efficient, scalable, and geometry-aware fine-tuning of large-scale 3D point cloud models.
  arXiv  Detail & Related papers  (2025-05-28T15:08:36Z)
• Wheat3DGS: In-field 3D Reconstruction, Instance Segmentation and Phenotyping of Wheat Heads with Gaussian Splatting [1.4100451538155885]
  We present Wheat3DGS, a novel approach that leverages 3DGS and the Segment Anything Model (SAM) for precise 3D instance segmentation and morphological measurement of hundreds of wheat heads automatically.<n>We validate the accuracy of wheat breeding head extraction against high-resolution laser scan data, obtaining per-instance mean absolute percentage errors of 15.1%, 18.3%, and 40.2% for length, width, and volume.
  arXiv  Detail & Related papers  (2025-04-09T15:31:42Z)
• MaizeField3D: A Curated 3D Point Cloud and Procedural Model Dataset of Field-Grown Maize from a Diversity Panel [12.89812013060155]
  We present a curated dataset of 3D point clouds of field-grown maize plants from a diverse genetic panel.<n>MaizeField3D will serve as a foundational dataset for AI-driven phenotyping, plant structural analysis, and 3D applications in agricultural research.
  arXiv  Detail & Related papers  (2025-03-10T19:53:20Z)
• Procedural Generation of 3D Maize Plant Architecture from LIDAR Data [16.458252508124794]
  This study introduces a robust framework for generating procedural 3D models of maize (Zea mays) plants from LiDAR point cloud data.<n>Our framework leverages Non-Uniform Rational B-Spline (NURBS) surfaces to model the leaves of maize plants.
  arXiv  Detail & Related papers  (2025-01-21T22:53:09Z)
• Mipmap-GS: Let Gaussians Deform with Scale-specific Mipmap for Anti-aliasing Rendering [81.88246351984908]
  We propose a unified optimization method to make Gaussians adaptive for arbitrary scales. Inspired by the mipmap technique, we design pseudo ground-truth for the target scale and propose a scale-consistency guidance loss to inject scale information into 3D Gaussians. Our method outperforms 3DGS in PSNR by an average of 9.25 dB for zoom-in and 10.40 dB for zoom-out.
  arXiv  Detail & Related papers  (2024-08-12T16:49:22Z)
• Improving Gaussian Splatting with Localized Points Management [52.009874685460694]
  Localized Point Management (LPM) is capable of identifying those error-contributing zones in greatest need for both point addition and geometry calibration.<n>LPM applies point densification in the identified zones and then reset the opacity of the points in front of these regions, creating a new opportunity to correct poorly conditioned points.<n> Notably, LPM improves both static 3DGS and dynamic SpaceTimeGS to achieve state-of-the-art rendering quality while retaining real-time speeds.
  arXiv  Detail & Related papers  (2024-06-06T16:55:07Z)
• SAGS: Structure-Aware 3D Gaussian Splatting [53.6730827668389]
  We propose a structure-aware Gaussian Splatting method (SAGS) that implicitly encodes the geometry of the scene. SAGS reflects to state-of-the-art rendering performance and reduced storage requirements on benchmark novel-view synthesis datasets.
  arXiv  Detail & Related papers  (2024-04-29T23:26:30Z)
• Eff-3DPSeg: 3D organ-level plant shoot segmentation using annotation-efficient point clouds [1.5882586857953638]
  We propose a novel weakly supervised framework, Eff-3DPSeg, for 3D plant shoot segmentation. High-resolution point clouds of soybean were reconstructed using a low-cost photogrammetry system. A weakly-supervised deep learning method was proposed for plant organ segmentation.
  arXiv  Detail & Related papers  (2022-12-20T14:09:37Z)
• Two-View Fine-grained Classification of Plant Species [66.75915278733197]
  We propose a novel method based on a two-view leaf image representation and a hierarchical classification strategy for fine-grained recognition of plant species. A deep metric based on Siamese convolutional neural networks is used to reduce the dependence on a large number of training samples and make the method scalable to new plant species.
  arXiv  Detail & Related papers  (2020-05-18T21:57:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.