Research map / Point clouds / Shape and surface completion
Cross-modal Learning for Image-Guided Point Cloud Shape Completion
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 |
|---|---|---|---|
| add the auxiliary image via cross-attention fusion (multimodal vs unimodal) (ablation) | XMFnet · ShapeNet-ViPC avg of 3 categories | Chamfer Distance x1e-3: 1.570 -> 1.470 | Helped |
| use best vs worst viewpoint image (ablation) | XMFnet · ShapeNet-ViPC avg of 3 categories | Chamfer Distance x1e-3: best 1.223, worst 1.819 vs avg 1.470 | Mixed |
| add mixup to resampling for weak supervision (ablation) | XMFnet weakly-sup. · ShapeNet-ViPC Airplane | Chamfer Distance x1e-3: 4.568 -> 4.239 | Helped |
| add differentiable silhouette rendering loss (ablation) | XMFnet weakly-sup. · ShapeNet-ViPC Airplane | Chamfer Distance x1e-3: 4.239 -> 2.426 | Helped |
| add density-aware Chamfer Distance to weak-supervision loss (ablation) | XMFnet weakly-sup. · ShapeNet-ViPC Cabinet | Chamfer Distance x1e-3: 3.012 -> 2.426 | Helped |
| latent cross-attention fusion instead of coarse point cloud from single-view reconstruction | XMFnet vs ViPC · ShapeNet-ViPC avg | Chamfer Distance x1e-3: 3.308 -> 1.443 | Helped |
| weakly-supervised image rendering supervision vs unimodal self-supervised VRC-Net | XMFnet · ShapeNet-ViPC Airplane/Lamp/Watercraft | Chamfer Distance x1e-3: 4.315 -> 2.426 (Airplane) | Helped |
Closest papers by meaning
- CDPNet: Cross-Modal Dual Phases Network for Point Cloud Completion (AAAI 2024 · similarity 0.90)
- DMF-Net: Image-Guided Point Cloud Completion with Dual-Channel Modality Fusion and Shape-Aware Upsampling Transformer (AAAI 2025 · similarity 0.90)
- Position-Aware Guided Point Cloud Completion with CLIP Model (AAAI 2025 · similarity 0.89)
- PCDreamer: Point Cloud Completion Through Multi-view Diffusion Priors (CVPR 2025 · similarity 0.88)
- PointAttN: You Only Need Attention for Point Cloud Completion (AAAI 2024 · similarity 0.87)
- PointMAC: Meta-Learned Adaptation for Robust Test-Time Point Cloud Completion (NeurIPS 2025 · 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.