NEST3D: A High-Resolution Multimodal Dataset of Sociable Weaver Tree Nests

2026-06-12

AI Summary

Existing ecological datasets lack detailed characterization of the intricate three-dimensional structures of sociable weaver nests, hindering high-fidelity modeling and analysis. To address this gap, this work presents an open-access, multimodal UAV dataset comprising 104 nest-bearing trees, integrating high-resolution RGB imagery, multispectral data, and dense 3D point clouds, along with expert-annotated semantic segmentation labels. This dataset establishes a novel benchmark for 3D semantic segmentation under extreme class imbalance by uniquely combining spectral, spatial, and structural information. Benchmark experiments using KPConv, RandLA-Net, and Point Transformer V3 demonstrate that Point Transformer V3 achieves a mean Intersection over Union (mIoU) of 86.35%, substantially outperforming convolution-based approaches and highlighting its superiority in complex ecological scenarios.

Abstract

Sociable weaver nests function as complex ecological structures offering thermoregulatory microhabitats and sustaining diverse species; however, datasets used in prior studies lack fine-grained 3D structural detail. Producing usable and accurate 3D weaver nest data is challenging due to their irregular geometry and integration with complex host vegetation. We bridge this gap with an open-access, 1.4 TB multimodal drone dataset of 104 nest-bearing trees, comprising 27,945 RGB images, 111,780 multispectral images, approximately 781 million 3D points, and expert-annotated semantic segmentation labels. We benchmark semantic segmentation using KPConv, RandLA-Net, and Point Transformer V3, with PT-v3 achieving an mIoU of 86.35% on the test set. While the results demonstrate strong performance for transformer-based and point-wise methods, they also highlight architecture-dependent challenges, particularly for convolution-based approaches such as KPConv. By uniquely combining spectral, spatial, and structural information, the presented dataset advances 3D reconstruction, segmentation, and classification algorithms, enabling ecological applications from nest volume estimation to species conservation, and serves as a demanding benchmark that exposes architecture-dependent performance under extreme class imbalance.

Problem

• 3D reconstruction
• sociable weaver nests
• multimodal dataset
• semantic segmentation
• ecological structures

Innovation

• multimodal drone dataset
• 3D point cloud segmentation
• semantic segmentation benchmark
• ecological 3D reconstruction
• Point Transformer