Research map / Image generation / Autoregressive and latent generation
Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Align 3D shape representations with image and text representations before conditional generation | Michelangelo · Text-conditioned generation | ST-S (ULIP): 10.293 -> 16.647 | Helped |
| Align 3D shape representations with image and text representations before conditional generation | Michelangelo · Text-conditioned generation | P-FID: 5.704 -> 2.075 | Helped |
| Use the shape-image-text aligned latent space for conditional generation (ablation) | ASLDM · Text-conditioned generation | semantic conformity to text | Helped |
| Use CLIP rather than SLIP in SITA-VAE (ablation) | SITA-VAE · Shape reconstruction and classification | reconstruction and classification performance | Helped |
| Use 512 learnable query embeddings (ablation) | SITA-VAE · Shape reconstruction and classification | reconstruction and classification performance | Helped |
Closest papers by meaning
- Sculpt3D: Multi-View Consistent Text-to-3D Generation with Sparse 3D Prior (CVPR 2024 · similarity 0.88)
- Text-conditional Attribute Alignment across Latent Spaces for 3D Controllable Face Image Synthesis (CVPR 2024 · similarity 0.88)
- GPLD3D: Latent Diffusion of 3D Shape Generative Models by Enforcing Geometric and Physical Priors (CVPR 2024 · similarity 0.87)
- ShapeLLM-Omni: A Native Multimodal LLM for 3D Generation and Understanding (NeurIPS 2025 · similarity 0.87)
- TextField3D: Towards Enhancing Open-Vocabulary 3D Generation with Noisy Text Fields (ICLR 2024 · similarity 0.87)
- PI3D: Efficient Text-to-3D Generation with Pseudo-Image Diffusion (CVPR 2024 · similarity 0.87)
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.