Research map / 3D vision / Face and shape
3D Shape Completion with Multi-View Consistent Inference
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 |
|---|---|---|---|
| Optimize the shape descriptor at inference with multi-view consistency and a generator-prior term | MVCN · ShapeNet test, Avg | Chamfer Distance (×100): 0.8298 -> 0.8052 | Helped |
| Use multi-view consistent inference | MVCN · ShapeNet test, Lamp | Chamfer Distance (×100): 1.0576 -> 1.1334 | Hurt |
| Add a generator loss that keeps predictions near the initial network output (ablation) | Multi-view consistent inference · Airplane models, 100-object analysis | Chamfer Distance (×10³): 6.383 -> 5.110 | Helped |
| Use L2 rather than L1 for generator loss at μ=1 (ablation) | Multi-view consistent inference · Airplane models, 100-object analysis | Chamfer Distance (×10³): 5.160 -> 5.110 | Helped |
| Increase μ from 1 to 2 with L1 generator loss (ablation) | Multi-view consistent inference · Airplane models, 100-object analysis | Chamfer Distance (×10³): 5.160 -> 5.129 | Helped |
| Increase pseudo-rendering depth-buffer size from U=1 to U=5 (ablation) | Multi-view consistent inference · ShapeNet test, Table | Chamfer Distance (×100): 0.8876 -> 0.8754 | Helped |
| Increase pseudo-rendering depth-buffer size from U=1 to U=5 (ablation) | Multi-view consistent inference · ShapeNet test, Sofa | Chamfer Distance (×100): 0.8440 -> 0.8394 | Helped |
| Pool consistency across more views, from J=3 to J=8 (ablation) | Multi-view consistent inference · ShapeNet test, Table | Chamfer Distance (×100): 0.8810 -> 0.8754 | Helped |
| Pool consistency across more views, from J=3 to J=8 (ablation) | Multi-view consistent inference · ShapeNet test, Sofa | Chamfer Distance (×100): 0.8484 -> 0.8394 | Helped |
| Optimize completed views directly without the conditional generative net | MVCN · ShapeNet completion | Chamfer Distance | Mixed |
Closest papers by meaning
- PCDreamer: Point Cloud Completion Through Multi-view Diffusion Priors (CVPR 2025 · similarity 0.89)
- FSC: Few-point Shape Completion (CVPR 2024 · similarity 0.88)
- DC-PCN: Point Cloud Completion Network with Dual-Codebook Guided Quantization (AAAI 2025 · similarity 0.88)
- Point-based Instance Completion with Scene Constraints (ICLR 2025 · similarity 0.87)
- CDPNet: Cross-Modal Dual Phases Network for Point Cloud Completion (AAAI 2024 · similarity 0.87)
- DinoComplete: 3D Shape Completion with Distilled Semantic Priors and State Space Models (NeurIPS 2026 · 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.