AI Paper Atlas

Research map / Point clouds / Shape and surface completion

PointTriNet: Learned Triangulation of 3D Point Sets

Nicholas Sharp, Maks Ovsjanikov

ECCV 2020 · Point clouds › Shape and surface completion · approach: Unsupervised shape correspondence · 56 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 neighboring triangles to the classification network input (ablation)PointTriNet · ShapeNetwatertight (%): 64.6 -> 77.0Improved
add neighboring triangles to the classification network input (ablation)PointTriNet · ShapeNetChamfer (x100): 0.8310 -> 0.7417Improved
add the proposal network instead of heuristic neighbor sampling (ablation)PointTriNet · ShapeNetwatertight (%): 66.4 -> 77.0Improved
add the proposal network instead of heuristic neighbor sampling (ablation)PointTriNet · ShapeNetChamfer (x100): 0.7748 -> 0.7417Improved
add the overlap loss (ablation)PointTriNet · ShapeNetwatertight (%): 76.0 -> 77.0Improved
add the overlap loss (ablation)PointTriNet · ShapeNetChamfer (x100): 0.7489 -> 0.7417Improved
replace Scan2Mesh-like dual-graph network with iterative PointNet classifier and proposalPointTriNet · ShapeNetwatertight (%): 23.3 -> 77.0Improved
replace Scan2Mesh-like dual-graph network with iterative PointNet classifier and proposalPointTriNet · ShapeNetChamfer (x100): 1.1887 -> 0.7417Improved
train PointTriNet from scratch on noisy points instead of clean pointsPointTriNet · ShapeNet noisyChamfer advantage over best classical: 0.7417 vs 0.9195 -> 1.0257 vs 1.2309Improved
use learned PointTriNet instead of ball pivotingPointTriNet · ShapeNetwatertight (%): 84.1 -> 77.0Hurt
use learned PointTriNet instead of ball pivotingPointTriNet · ShapeNetChamfer (x100): 1.3440 -> 0.7417Improved
remove batch or layer normalization (ablation)PointTriNet · ShapeNetresult qualityImproved

Later papers that compared with this method

4 later accepted papers report PointTriNet as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.

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