Research map / Point clouds / Shape and surface completion
EC-Net: an Edge-aware Point set Consolidation Network
Lequan Yu, Xianzhi Li, Chi-Wing Fu, Daniel Cohen-Or, Pheng-Ann Heng
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 edge-aware joint loss with direct point-to-surface distance instead of EMD loss (PU-Net) | point cloud consolidation · Point-to-mesh distance, Chair (virtual scans) | mean distance (1e-3): 1.70 -> 0.88 | Improved |
| use EC-Net instead of PU-Net | point cloud consolidation · Point-to-mesh distance, Fandisk (virtual scans) | mean distance (1e-3): 2.86 -> 1.09 | Improved |
| use EC-Net instead of EAR | point cloud consolidation · Point-to-mesh distance, Headphone (virtual scans) | mean distance (1e-3): 3.71 -> 0.81 | Improved |
| use EC-Net instead of EAR | point cloud consolidation · Point-to-mesh distance, Sofa (virtual scans) | mean distance (1e-3): 1.56 -> 1.72 | Hurt |
| replace PCA plane fitting denoising with EC-Net consolidation before BPA reconstruction | surface reconstruction · Reconstruction on virtual scans | mean Hausdorff distance | Improved |
Later papers that compared with this method
4 later accepted papers report EC-Net as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.
- STAR-Edge: Structure-aware Local Spherical Curve Representation for Thin-walled Edge Extraction from Unstructured Point Clouds (CVPR 2025 · better on 2 of 2 shared results)
- NerVE: Neural Volumetric Edges for Parametric Curve Extraction From Point Cloud (CVPR 2023 · better on 2 of 2 shared results)
- PC2WF: 3D Wireframe Reconstruction from Raw Point Clouds (ICLR 2021 · better on 2 of 2 shared results)
- PIE-NET: Parametric Inference of Point Cloud Edges (NeurIPS 2020 · better on 4 of 4 shared results)
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
- EdgeMovingNet: Edge-preserving Point Cloud Reconstruction via Joint Geometry Features (CVPR 2025 · similarity 0.90)
- Meshing Point Clouds with Predicted Intrinsic-Extrinsic Ratio Guidance (ECCV 2020 · similarity 0.89)
- PU-Net: Point Cloud Upsampling Network (CVPR 2018 · similarity 0.89)
- A Survey and Benchmark of Automatic Surface Reconstruction From Point Clouds (TPAMI 2024 · similarity 0.88)
- DANCE: Density-agnostic and Class-aware Network for Point Cloud Completion (AAAI 2026 · similarity 0.88)
- LinNet: Linear Network for Efficient Point Cloud Representation Learning (NeurIPS 2024 · similarity 0.88)
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.
