Research map / 3D vision / Face and shape
NeuraLeaf: Neural Parametric Leaf Models with Shape and Deformation Disentanglement
Yang Yang, Dongni Mao, Hiroaki Santo, Yasuyuki Matsushita, Fumio Okura
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 |
|---|---|---|---|
| add deformation mapping loss L_map (ablation) | NeuraLeaf · DeformLeaf single leaf | Chamfer-L2 (mm): 5.3 -> 2.1 | Improved |
| add shape encoder for latent initialization (ablation) | NeuraLeaf · DeformLeaf single leaf | Chamfer-L2 (mm): 9.8 -> 2.1 | Improved |
| add deformation encoder for latent initialization (ablation) | NeuraLeaf · DeformLeaf single leaf | Chamfer-L2 (mm): 14.7 -> 2.1 | Improved |
| increase control points from 100 to 1000 (ablation) | NeuraLeaf · DeformLeaf single leaf | Chamfer-L2 (mm): 13.7 -> 2.1 | Improved |
| increase control points from 500 to 1000 (ablation) | NeuraLeaf · DeformLeaf single leaf | Chamfer-L2 (mm): 8.3 -> 2.1 | Improved |
| optimize control points (ablation) | NeuraLeaf · DeformLeaf single leaf | Chamfer-L2 (mm): 21.4 -> 2.1 | Improved |
| add boundary length loss L_bound (ablation) | NeuraLeaf · DeformLeaf single leaf | Chamfer-L2 (mm): 9.4 -> 2.1 | Improved |
| add face angle loss L_ang (ablation) | NeuraLeaf · DeformLeaf single leaf | Chamfer-L2 (mm): 4.3 -> 2.1 | Improved |
| share shape latent among leaves of a plant (ablation) | NeuraLeaf · Multiple-leaf reconstruction | Chamfer-L2 (mm): 117.14 -> 31.74 | Improved |
| use NeuraLeaf instead of NPM | NPM · Multiple-leaf reconstruction | Chamfer-L2 (mm): 57.29 -> 31.74 | Improved |
Closest papers by meaning
- NeuraLeaf: Disentangled Neural Parametric Modeling of Leaf Shape, Deformation, and Appearance (IJCV 2026 · similarity 0.99)
- Neural Hierarchical Decomposition for Single Image Plant Modeling (CVPR 2025 · similarity 0.89)
- Learning to Infer Parameterized Representations of Plants from 3D Scans (CVPR 2026 · similarity 0.89)
- Demeter: A Parametric Model of Crop Plant Morphology from the Real World (ICCV 2025 · similarity 0.89)
- SVDTree: Semantic Voxel Diffusion for Single Image Tree Reconstruction (CVPR 2024 · similarity 0.84)
- Geometry-Centered 3D Latent World Models for Growing Surfaces (NeurIPS 2026 · similarity 0.83)
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.
