AI Paper Atlas

Research map / Point clouds / Shape and surface completion

DeepDT: Learning Geometry From Delaunay Triangulation for Surface Reconstruction

Yiming Luo, Zhenxing Mi, Wenbing Tao

AAAI 2021 · Point clouds › Shape and surface completion · approach: Unsupervised shape correspondence · 41 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
Use DeepDT instead of SSRNetsurface reconstruction on ShapeNet · ShapeNetChamfer-L1: 0.24 -> 0.20Improved
Use DeepDT instead of SSRNetsurface reconstruction on ShapeNet · ShapeNetNC: 0.967 -> 0.967No clear effect
Use DeepDT instead of SSRNetsurface reconstruction on DTU · DTUDC-Mean: 0.30 -> 0.37Hurt
Use DeepDT instead of SSRNetsurface reconstruction on DTU · DTUDC-Var.: 0.09 -> 0.15Hurt
Use DeepDT instead of PSRsurface reconstruction on DTU · DTUCD-Mean: 1.17 -> 0.68Improved
Use DeepDT instead of SSRNet-SShapeNet-trained reconstruction model evaluated without retraining · Stanford 3D ArmadilloCD Mean: 0.028 -> 0.021Improved
Use DeepDT instead of SSRNet-SShapeNet-trained reconstruction model evaluated without retraining · Stanford 3D ArmadilloCD RMS: 0.131 -> 0.028Improved
Use DeepDT instead of SSRNet-SShapeNet-trained reconstruction model evaluated without retraining · Stanford 3D BunnyCD Mean: 0.064 -> 0.038Improved
Use DeepDT instead of SSRNet-SShapeNet-trained reconstruction model evaluated without retraining · Stanford 3D BunnyCD RMS: 0.134 -> 0.095Improved
Use DeepDT instead of SSRNet-SShapeNet-trained reconstruction model evaluated without retraining · Stanford 3D DragonCD Mean: 0.053 -> 0.029Improved
Use DeepDT instead of SSRNet-SShapeNet-trained reconstruction model evaluated without retraining · Stanford 3D DragonCD RMS: 0.208 -> 0.081Improved
Use DeepDT instead of SSRNetDTU scan reconstruction · DTUtime per scan (seconds): 139.652 seconds -> 8.985 secondsImproved

Later papers that compared with this method

1 later accepted paper reports DeepDT as a baseline in their results tables; 1 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 0 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