Research map / Point clouds / Shape and surface completion
ME-PCN: Point Completion Conditioned on Mask Emptiness
Bingchen Gong, Yinyu Nie, Yiqun Lin, Xiaoguang Han, Yizhou Yu
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 ray emptiness features to MSN encoder (ablation) | MSN · ShapeNet 6 categories (8192 pts) | EMD x100: 8.19 -> 6.52 | Improved |
| add ray emptiness features to MSN encoder (ablation) | MSN · ShapeNet 6 categories (8192 pts) | CD x100: 5.77 -> 4.67 | Improved |
| add ray emptiness features to PCN (ablation) | PCN · ShapeNet 6 categories (8192 pts) | EMD x100: 12.77 -> 11.30 | Improved |
| add ray emptiness features to PCN (ablation) | PCN · ShapeNet 6 categories (8192 pts) | CD x100: 4.45 -> 3.94 | Improved |
| add ray emptiness features to PCN (ablation) | PCN · ShapeNet 6 categories (2048 pts) | EMD x100: 13.54 -> 12.44 | Improved |
| add ray emptiness features to PCN (ablation) | PCN · ShapeNet 6 categories (2048 pts) | CD x100: 6.48 -> 5.74 | Improved |
| use 3D ray emptiness encoding instead of 2D convolution encoding (ablation) | ME-PCN · ShapeNet 6 categories (8192 pts) | EMD x100: 6.51 -> 5.93 | Improved |
| use 3D ray emptiness encoding instead of 2D convolution encoding (ablation) | ME-PCN · ShapeNet 6 categories (8192 pts) | CD x100: 4.25 -> 3.71 | Improved |
| fine-tune on strongly noised masks (ablation) | ME-PCN · ShapeNet chair | EMD x100: 5.12 -> 5.26 | No clear effect |
| fine-tune on strongly noised masks (ablation) | ME-PCN · ShapeNet table | EMD x100: 5.33 -> 5.56 | No clear effect |
| fine-tune on strongly noised masks (ablation) | ME-PCN · ShapeNet chair | CD x100: 3.62 -> 3.67 | No clear effect |
| fine-tune on strongly noised masks (ablation) | ME-PCN · ShapeNet table | CD x100: 3.76 -> 3.92 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- GRNet — GRNet: Gridding Residual Network for Dense Point Cloud Completion (ECCV 2020) · better on 4 of 4 shared results
- PF-Net — PF-Net: Point Fractal Network for 3D Point Cloud Completion (CVPR 2020) · better on 2 of 2 shared results
- SoftPoolNet — SoftPoolNet: Shape Descriptor for Point Cloud Completion and Classification (ECCV 2020) · better on 2 of 2 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
- Skeleton-bridged Point Completion: From Global Inference to Local Adjustment (NeurIPS 2020 · similarity 0.92)
- Point Cloud Completion by Skip-Attention Network With Hierarchical Folding (CVPR 2020 · similarity 0.90)
- Rethinking Multimodal Point Cloud Completion: A Completion-by-Correction Perspective (AAAI 2026 · similarity 0.89)
- DC-PCN: Point Cloud Completion Network with Dual-Codebook Guided Quantization (AAAI 2025 · similarity 0.89)
- FSC: Few-point Shape Completion (CVPR 2024 · similarity 0.88)
- Digging into Intrinsic Contextual Information for High-fidelity 3D Point Cloud Completion (AAAI 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.
