Research map / Point clouds / Shape and surface completion
MorphoGen: Efficient Unconditional Generation of Long-Range Projection Neuronal Morphology via a Global-to-Local Framework
Tianfang Zhu, Hongyang Zhou, Anan Li
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 |
|---|---|---|---|
| replace branch-sequential generation with global point-cloud diffusion | MorphGrower · PT neurons | 1-NNA (CD, %): 94.036 -> 66.292 | Improved |
| replace branch-sequential generation with global point-cloud diffusion | MorphGrower · CT neurons | 1-NNA (CD, %): 91.994 -> 74.780 | Improved |
| replace branch-sequential generation with global point-cloud diffusion | MorphGrower · IT neurons | 1-NNA (CD, %): 72.134 -> 66.490 | Improved |
| replace branch-sequential generation with global point-cloud diffusion | MorphGrower · IT neurons | COV (CD, %): 14.924 -> 12.081 | Hurt |
| replace branch-sequential generation with global point-cloud diffusion | MorphGrower · IT neurons | JSD: 0.13343 -> 0.15860 | Hurt |
| replace branch-sequential generation with global point-cloud diffusion | MorphGrower · PT neurons | JSD: 0.23201 -> 0.12368 | Improved |
| replace branch-sequential generation with global point-cloud diffusion | MorphGrower · PT neurons | training time (hours): 195 -> 33 | Improved |
| replace branch-sequential generation with global point-cloud diffusion | MorphGrower · CT neurons | training time (hours): 37 -> 33 | Mixed |
| use point-cloud diffusion with skeleton linking instead of 3D-walk VAE | MorphVAE · IT neurons | 1-NNA (CD, %): 100 -> 66.490 | Improved |
| remove need for real reference data at inference | MorphGrower · CT neurons | MMD (CD): 0.02160 -> 0.01624 | Improved |
Closest papers by meaning
- MorphGrower: A Synchronized Layer-by-layer Growing Approach for Plausible Neuronal Morphology Generation (ICML 2024 · similarity 0.92)
- Neuroformer: Multimodal and Multitask Generative Pretraining for Brain Data (ICLR 2024 · similarity 0.85)
- DiffeoMorph: Learning to Morph 3D Shapes Using Differentiable Agent-Based Simulations (NeurIPS 2026 · similarity 0.85)
- Neuron Platonic Intrinsic Representation From Dynamics Using Contrastive Learning (ICLR 2025 · similarity 0.85)
- Neuron Populations Exhibit Divergent Selectivity with Scale (NeurIPS 2026 · similarity 0.84)
- Latent Diffusion for Neural Spiking Data (NeurIPS 2024 · similarity 0.84)
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.
