Research map / Point clouds / Shape and surface completion
RFNet: Recurrent Forward Network for Dense Point Cloud Completion
Tianxin Huang, Hao Zou, Jinhao Cui, Xuemeng Yang, Mengmeng Wang, Xiangrui Zhao, Jiangning Zhang, Yi Yuan, Yifan Xu, Yong Liu
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 Sampling Chamfer Distance to Encode Cell only model (ablation) | RFNet · ShapeNet known categories | CD x10^3: 9.35 -> 9.27 | Improved |
| add Sampling Chamfer Distance to Encode Cell only model (ablation) | RFNet · ShapeNet known categories | FD x10^3: 6.86 -> 6.58 | Improved |
| add Refine Cell and Merge Layer to Encode Cell + SCD (ablation) | RFNet · ShapeNet known categories | CD x10^3: 9.27 -> 8.44 | Improved |
| add Refine Cell and Merge Layer to Encode Cell + SCD (ablation) | RFNet · ShapeNet known categories | FD x10^3: 6.58 -> 3.58 | Improved |
| add Balanced Expansion Constraint to Encode Cell + SCD (ablation) | RFNet · ShapeNet known categories | CD x10^3: 9.27 -> 9.26 | No clear effect |
| add Balanced Expansion Constraint to Encode Cell + SCD (ablation) | RFNet · ShapeNet known categories | CD* at 0.08M iterations: 9.81 -> 9.72 | Improved |
| add Recover Cell (ablation) | RFNet · ShapeNet known categories | CD x10^3: 9.26 -> 8.96 | Improved |
| add Recover Cell (ablation) | RFNet · ShapeNet known categories | FD x10^3: 6.59 -> 6.44 | Improved |
| add Refine Cell (ablation) | RFNet · ShapeNet known categories | CD x10^3: 8.96 -> 8.80 | Improved |
| add Merge Layer (Raw Shape Protection) (ablation) | RFNet · ShapeNet known categories | CD x10^3: 8.80 -> 8.13 | Improved |
| add Merge Layer (Raw Shape Protection) (ablation) | RFNet · ShapeNet known categories | FD x10^3: 6.34 -> 3.35 | Improved |
| add Merge Layer (Raw Shape Protection) (ablation) | RFNet · ShapeNet known categories | CD* at 0.08M iterations: 9.29 -> 8.46 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- GRNet — GRNet: Gridding Residual Network for Dense Point Cloud Completion (ECCV 2020) · better on 5 of 7 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
- GRNet: Gridding Residual Network for Dense Point Cloud Completion (ECCV 2020 · similarity 0.89)
- FBNet: Feedback Network for Point Cloud Completion (ECCV 2022 · similarity 0.89)
- PF-Net: Point Fractal Network for 3D Point Cloud Completion (CVPR 2020 · similarity 0.88)
- Hyper-PCN: Hypergraph-Based Point Cloud Completion via High-Order Correlation Modeling (CVPR 2026 · similarity 0.88)
- CDPNet: Cross-Modal Dual Phases Network for Point Cloud Completion (AAAI 2024 · similarity 0.87)
- DC-PCN: Point Cloud Completion Network with Dual-Codebook Guided Quantization (AAAI 2025 · similarity 0.86)
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.
