Research map / Point clouds / Shape and surface completion
VPP: Efficient Conditional 3D Generation via Voxel-Point Progressive Representation
Zekun Qi, Muzhou Yu, Runpei Dong, Kaisheng Ma
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 VPP instead of Point-E on text-conditioned generation | VPP · ShapeNetCore13 | FID: 85.37 -> 29.82 | Improved |
| Use VPP instead of CLIP-Sculptor | VPP · ShapeNetCore13 | FID: 1480.11 -> 29.82 | Improved |
| Use VPP instead of CLIP-Sculptor | VPP · ShapeNetCore13 | ACC: 87.08 -> 88.04 | Improved |
| Use VPP instead of Point-E | VPP · ShapeNetCore13 | IS: 7.93 -> 10.64 | Improved |
| Add test-time voting to fine-tuned VPP (ablation) | VPP · ScanObjectNN PB_T50_RS | accuracy: 88.65 -> 89.28 | Improved |
| Add test-time voting to fine-tuned VPP (ablation) | VPP · ScanObjectNN OBJ_BG | accuracy: 92.77 -> 93.11 | Improved |
| Add test-time voting to fine-tuned VPP (ablation) | VPP · ModelNet40 8k points | accuracy: 94.0 -> 94.3 | Improved |
| Use VPP pretraining instead of Point-MAE | VPP · ScanObjectNN PB_T50_RS | accuracy: 85.18 -> 89.28 | Improved |
| Use VPP pretraining instead of Point-MAE | VPP · ModelNet40 1k points | accuracy: 93.8 -> 94.1 | Improved |
| Compare with cross-modal teacher method ReCon | VPP · ScanObjectNN PB_T50_RS | accuracy: 90.63 -> 89.28 | Hurt |
| Few-shot 10-way 10-shot versus Point-M2AE | VPP · ModelNet40 few-shot | accuracy: 92.3 -> 93.0 | Improved |
| Vary image-text feature ratio and Gaussian noise strength (too large or too small) (ablation) | VPP training · ShapeNet generation | quality and diversity | Mixed |
Closest papers by meaning
- PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers (NeurIPS 2025 · similarity 0.87)
- ARMesh: Autoregressive Mesh Generation via Next-Level-of-Detail Prediction (NeurIPS 2025 · similarity 0.87)
- Sculpt3D: Multi-View Consistent Text-to-3D Generation with Sparse 3D Prior (CVPR 2024 · similarity 0.87)
- Ouroboros3D: Image-to-3D Generation via 3D-aware Recursive Diffusion (CVPR 2025 · similarity 0.86)
- MeshArt: Generating Articulated Meshes with Structure-Guided Transformers (CVPR 2025 · similarity 0.86)
- Efficient Part-level 3D Object Generation via Dual Volume Packing (NeurIPS 2025 · similarity 0.86)
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.
