AI Paper Atlas

Research map / Point clouds / Shape and surface completion

DeepFit: 3D Surface Fitting via Neural Network Weighted Least Squares

Yizhak Ben-Shabat, Stephen Gould

ECCV 2020 · Point clouds › Shape and surface completion · approach: Point cloud upsampling and normals

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
use a larger neighborhood (k=256 vs 64 points) (ablation)DeepFit · PCPNet normals, high noiseRMSEImproved
use a larger neighborhood (more points) (ablation)DeepFit · PCPNet normals, no noiseRMSEHurt
raise the jet order from 1 to 2-4 (ablation)DeepFit · PCPNet normals, low and medium noiseRMSEMixed
vary jet order n=1,2,3,4 (ablation)DeepFit · PCPNet normalsRMSENo clear effect
use DeepFit weighted fitting instead of single-scale PCPNetPCPNet · PCPNet normals (average)RMSE angle error: 14.56 -> 11.8Improved
use multiple scales instead of one in PCPNetPCPNet · PCPNet normals (average)RMSE angle error: 14.56 -> 14.34No clear effect
use DeepFit instead of PCPNet for maximum curvaturePCPNet · PCPNet curvature k1normalized RMSE: 1.38 -> 0.89Improved
use DeepFit instead of PCPNet for minimum curvaturePCPNet · PCPNet curvature k2normalized RMSE: 0.54 -> 0.466Improved
use DeepFit instead of Lenssen et al. under high noiseLenssen et al. · PCPNet normals, noise 0.012RMSE angle error: 21.96 -> 23.12Hurt

Later papers that compared with this method

7 later accepted papers report DeepFit as a baseline in their results tables; 7 of them report a better number on most of the results they share with it.

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