Research map / Point clouds / Shape and surface completion
EINet: Point Cloud Completion via Extrapolation and Interpolation
Pingping Cai, Canyu Zhang, LINGJIA SHI, Lili Wang, Nasrin Imanpour, Song Wang
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 |
|---|---|---|---|
| add the Seed Feature Propagation module (coordinate and feature differences) instead of 3-NN propagation (ablation) | EINet · PCN | CD-L1 (x10^-3): 6.87 -> 6.63 | Improved |
| add the feature-space Extrapolation module instead of SnowFlake seed head (ablation) | EINet · PCN | CD-L1 (x10^-3): 7.02 -> 6.63 | Improved |
| add the Mapping Constraint loss (ablation) | EINet · PCN | CD-L1 (x10^-3): 6.69 -> 6.63 | Improved |
| use EINet instead of PoinTr in model size | point cloud completion · PCN model complexity | parameters (M): 28.9 -> 2.80 | Improved |
| use EINet instead of AdaPoinTr | point cloud completion · PCN | CD-L1 (x10^-3): 6.53 -> 6.63 | Hurt |
| use EINet instead of AdaPoinTr on ShapeNet-55 | point cloud completion · ShapeNet-55 | CD-Avg (CD-L2 x10^-3): 0.81 -> 0.90 | Hurt |
| use EINet instead of SeedFormer on PCN | point cloud completion · PCN | CD-L1 (x10^-3): 6.74 -> 6.63 | Improved |
Later papers that compared with this method
2 later accepted papers report EINet as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- Simba: Towards High-Fidelity and Geometrically-Consistent Point Cloud Completion via Transformation Diffusion (AAAI 2026 · better on 1 of 1 shared result)
- PointMAC: Meta-Learned Adaptation for Robust Test-Time Point Cloud Completion (NeurIPS 2025 · better on 1 of 1 shared result)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 4 on most shared results.
- AdaPoinTr — AdaPoinTr: Diverse Point Cloud Completion With Adaptive Geometry-Aware Transformers (TPAMI 2023) · better on 0 of 6 shared results
- SeedFormer — SeedFormer: Patch Seeds Based Point Cloud Completion with Upsample Transformer (ECCV 2022) · better on 4 of 4 shared results
- PoinTr — PoinTr: Diverse Point Cloud Completion With Geometry-Aware Transformers (ICCV 2021) · better on 2 of 2 shared results
- ProxyFormer — ProxyFormer: Proxy Alignment Assisted Point Cloud Completion With Missing Part Sensitive Transformer (CVPR 2023) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- CRA-PCN: Point Cloud Completion with Intra- and Inter-level Cross-Resolution Transformers (AAAI 2024 · similarity 0.89)
- Position-Aware Guided Point Cloud Completion with CLIP Model (AAAI 2025 · similarity 0.88)
- PLATYPUS: Progressive Local Surface Estimator for Arbitrary-Scale Point Cloud Upsampling (AAAI 2025 · similarity 0.88)
- ComPC: Completing a 3D Point Cloud with 2D Diffusion Priors (ICLR 2025 · similarity 0.88)
- SPU-IMR: Self-supervised Arbitrary-scale Point Cloud Upsampling via Iterative Mask-recovery Network (AAAI 2025 · similarity 0.88)
- Point-based Instance Completion with Scene Constraints (ICLR 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.
