The ultimate goal of this research is the complete virtualization of plants from sensing data, i.e., the generation of a plant digital twin. This research focuses particularly on technical elements related to computer vision, and reproduces not only the shape of the plant from a set of images taken of the plant, but also its branch and leaf structure, time-series changes, etc., including occluded areas. The virtualized plant model enables simulation and mapping to genes, and is a powerful tool for automating cultivation and accelerating breeding.

Grants

• 2021/4～2028/3 JST FOREST
  “PlantTwin: Reconstructing plants for breeding and cultivation”
  PI: Fumio Okura, Grant: 50,000K JPY

Publications

• Xinpeng Liu, Zeyi Huang, Fumio Okura, Yasuyuki Matsushita. HoGS: Unified near and far object reconstruction via homogeneous gaussian splatting. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025.
• Xinpeng Liu, Hiroaki Santo, Yosuke Toda, Fumio Okura: TreeFormer: Single-view plant skeleton estimation via tree-constrained graph generation. Proc. IEEE/CVF Winter Conference on Applications of Computer Vision (WACV’25), Feb 2025. [arXiv] [code]
• Takuto Narumoto, Hiroaki Santo, Fumio Okura. Synthesizing time-varying BRDFs via latent space.
  Proceedings of European Conference on Computer Vision (ECCV), 2024. [Paper]
• Satoru Tsugawa, Kaname Teratsuji, Fumio Okura, Koji Noshita, Masaki Tateno, Jingyao Zhang, Taku Demura: Exploring the mechanical and morphological rationality of tree branch structure based on 3D point cloud analysis and the finite element method. Scientific Reports, Vol. 12, Article No 4054, Mar 2022. [paper]
• Fumio Okura: 3D modeling and reconstruction of plants and trees: A cross-cutting review across computer graphics, vision, and plant phenotyping. Breeding Science, Vol. 72, Issue 1, pp. 31-47, Feb 2022. [paper]