GrowSplat: Constructing Temporal Digital Twins of Plants with Gaussian Splats

Accurate temporal reconstructions of plant growth are essential for plant phenotyping and breeding, yet remain challenging due to complex geometries, occlusions, and non-rigid deformations of plants. We present a novel framework for building temporal digital twins of plants by combining 3D Gaussian Splatting with a robust sample alignment pipeline. Our method begins by reconstructing Gaussian Splats from multi-view camera data, then leverages a two-stage registration approach: coarse alignment through feature-based matching and Fast Global Registration, followed by fine alignment with Iterative Closest Point. This pipeline yields a consistent 4D model of plant development in discrete time steps. We evaluate the approach on data from the Netherlands Plant Eco-phenotyping Center, demonstrating detailed temporal reconstructions of Sequoia and Quinoa species. Videos and Images can be seen atthis https URL

@article{adebola2025_2505.10923,
  title={ GrowSplat: Constructing Temporal Digital Twins of Plants with Gaussian Splats },
  author={ Simeon Adebola and Shuangyu Xie and Chung Min Kim and Justin Kerr and Bart M. van Marrewijk and Mieke van Vlaardingen and Tim van Daalen and Robert van Loo and Jose Luis Susa Rincon and Eugen Solowjow and Rick van de Zedde and Ken Goldberg },
  journal={arXiv preprint arXiv:2505.10923},
  year={ 2025 }
}