AI Paper Atlas

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

ICCV 2021 · Point clouds › Shape and surface completion · approach: Point cloud completion networks · 46 citations (OpenAlex)

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 changedWhereMeasuredEffect
add Sampling Chamfer Distance to Encode Cell only model (ablation)RFNet · ShapeNet known categoriesCD x10^3: 9.35 -> 9.27Improved
add Sampling Chamfer Distance to Encode Cell only model (ablation)RFNet · ShapeNet known categoriesFD x10^3: 6.86 -> 6.58Improved
add Refine Cell and Merge Layer to Encode Cell + SCD (ablation)RFNet · ShapeNet known categoriesCD x10^3: 9.27 -> 8.44Improved
add Refine Cell and Merge Layer to Encode Cell + SCD (ablation)RFNet · ShapeNet known categoriesFD x10^3: 6.58 -> 3.58Improved
add Balanced Expansion Constraint to Encode Cell + SCD (ablation)RFNet · ShapeNet known categoriesCD x10^3: 9.27 -> 9.26No clear effect
add Balanced Expansion Constraint to Encode Cell + SCD (ablation)RFNet · ShapeNet known categoriesCD* at 0.08M iterations: 9.81 -> 9.72Improved
add Recover Cell (ablation)RFNet · ShapeNet known categoriesCD x10^3: 9.26 -> 8.96Improved
add Recover Cell (ablation)RFNet · ShapeNet known categoriesFD x10^3: 6.59 -> 6.44Improved
add Refine Cell (ablation)RFNet · ShapeNet known categoriesCD x10^3: 8.96 -> 8.80Improved
add Merge Layer (Raw Shape Protection) (ablation)RFNet · ShapeNet known categoriesCD x10^3: 8.80 -> 8.13Improved
add Merge Layer (Raw Shape Protection) (ablation)RFNet · ShapeNet known categoriesFD x10^3: 6.34 -> 3.35Improved
add Merge Layer (Raw Shape Protection) (ablation)RFNet · ShapeNet known categoriesCD* at 0.08M iterations: 9.29 -> 8.46Improved

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy