AI Paper Atlas

Research map / Point clouds / Shape and surface completion

GRNet: Gridding Residual Network for Dense Point Cloud Completion

Haozhe Xie, Hongxun Yao, Shangchen Zhou, Jiageng Mao, Shengping Zhang, Wenxiu Sun

ECCV 2020 · Point clouds › Shape and surface completion · approach: Structure-guided completion · 457 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
replace prior methods with GRNetbest prior (PCN) · ShapeNetChamfer Distance overall (x10^-4): 4.016 -> 2.723Improved
use GRNetMSN · ShapeNetF-Score@1% overall: 0.705 -> 0.708Improved
use GRNetTopNet · Completion3DChamfer Distance overall (x10^-4): 14.25 -> 10.64Improved
use GRNetTopNet · KITTIConsistency (x10^-3): 0.568 -> 0.313Improved
use GRNetMSN · KITTIFidelity Distance (x10^3): 0.434 -> 0.816Hurt
increase Gridding resolution from 32^3 to 64^3 (ablation)GRNet · ShapeNetChamfer Distance complete (x10^-4): 5.943 -> 2.723Improved
increase Gridding resolution from 64^3 to 128^3 (ablation)GRNet · ShapeNetChamfer Distance complete (x10^-4): 2.723 -> 2.732No clear effect
add Cubic Feature Sampling with three feature maps (ablation)GRNet · ShapeNetChamfer Distance (x10^-4): 11.375 -> 2.723Improved
add more feature maps into Cubic Feature Sampling (one to three) (ablation)GRNet · ShapeNetChamfer Distance (x10^-4): 2.922 -> 2.723Improved
add Gridding Loss (ablation)GRNet · ShapeNetChamfer Distance complete (x10^-4): 4.460 -> 2.723Improved
add Gridding Loss (ablation)GRNet · ShapeNetF-Score@1% complete: 0.624 -> 0.708Improved
increase Gridding Loss resolution from 64^3 to 128^3 (ablation)GRNet · ShapeNetChamfer Distance complete (x10^-4): 3.427 -> 2.723Improved

Later papers that compared with this method

25 later accepted papers report GRNet as a baseline in their results tables; 21 of them report a better number on most of the results they share with it.

17 more not listed.

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