Research map / 3D vision / Face and shape
Demeter: A Parametric Model of Crop Plant Morphology from the Real World
Tianhang Cheng, Albert J. Zhai, Evan Z. Chen, Rui Zhou, Yawen Deng, Zitong Li, Kejie Zhao, Janice Shiu, Qianyu Zhao, Yide Xu, Xinlei Wang, Yuan Shen and 4 more
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use Demeter instead of procedural SimpProc for soybean fitting | Demeter · Soybean 3D reconstruction | Chamfer distance: 0.0376 -> 0.0016 | Improved |
| use Demeter instead of procedural SimpProc for maize fitting | Demeter · Maize 3D reconstruction | Chamfer distance: 0.0557 -> 0.0071 | Improved |
| use Demeter instead of neural NKSR on soybean | Demeter · Soybean 3D reconstruction | Chamfer distance: 0.0030 -> 0.0016 | Improved |
| use Demeter instead of NKSR on maize | Demeter · Maize 3D reconstruction | Chamfer distance: 0.0023 -> 0.0071 | Hurt |
| use Demeter instead of dense-mesh NKSR for storage on soybean | Demeter · Soybean 3D reconstruction | storage size (KB): 5785.6 -> 3.3750 | Improved |
| use Demeter instead of NKSR for storage on maize | Demeter · Maize 3D reconstruction | storage size (KB): 3686.4 -> 1.7656 | Improved |
| use Demeter instead of SimpProc for storage on soybean | Demeter · Soybean 3D reconstruction | storage size (KB): 0.2754 -> 3.3750 | Hurt |
| use Demeter-fitted shapes instead of Meshy for single-view reconstruction | Demeter · Single-view plant reconstruction | mask IoU: 0.206 -> 0.328 | Improved |
| use Demeter instead of Zero123++ for single-view reconstruction | Demeter · Single-view plant reconstruction | mask IoU: 0.296 -> 0.328 | Improved |
Closest papers by meaning
- NeuraLeaf: Neural Parametric Leaf Models with Shape and Deformation Disentanglement (ICCV 2025 · similarity 0.89)
- NeuraLeaf: Disentangled Neural Parametric Modeling of Leaf Shape, Deformation, and Appearance (IJCV 2026 · similarity 0.89)
- Neural Hierarchical Decomposition for Single Image Plant Modeling (CVPR 2025 · similarity 0.87)
- Geometry-Centered 3D Latent World Models for Growing Surfaces (NeurIPS 2026 · similarity 0.84)
- SVDTree: Semantic Voxel Diffusion for Single Image Tree Reconstruction (CVPR 2024 · similarity 0.83)
- AgMMU: A Comprehensive Agricultural Multimodal Understanding Benchmark (NeurIPS 2025 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
