AI Paper Atlas

Research map / Point clouds / Shape and surface completion

BAE-NET: Branched Autoencoder for Shape Co-Segmentation

Zhiqin Chen, Kangxue Yin, Matthew Fisher, Siddhartha Chaudhuri, Hao Zhang

ICCV 2019 · Point clouds › Shape and surface completion · approach: Unsupervised shape correspondence · 122 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 table shapes to chair training set (joint chair+table) (ablation)BAE-NET unsupervised · ShapeNet part chairIOU: 65.5 -> 83.7Improved
allow part combinations when scoring (mod-IOU instead of IOU)BAE-NET unsupervised · ShapeNet part airplaneIOU: 61.1 -> 80.4Improved
allow part combinations when scoring (mod-IOU instead of IOU)BAE-NET unsupervised · ShapeNet part skateboardIOU: 63.5 -> 88.1Improved
allow part combinations when scoring (mod-IOU instead of IOU)BAE-NET unsupervised · ShapeNet part tableIOU: 78.7 -> 87.0Improved
use 3-layer decoder instead of 2-layer decoder (ablation)BAE-NET · synthetic 2D elements and triple ringsqualitative part separationImproved
use 3-layer decoder instead of 4-layer decoder (ablation)BAE-NET · synthetic 2D shapesqualitative part separationImproved
use branched fully connected decoder instead of CNN decoder (ablation)BAE-NET · synthetic 2D shapesqualitative part separationImproved
alter data distribution so only 20% of shapes have target part (ablation)BAE-NET · Tags2Parts datasetsqualitative part separationImproved
use BAE-NET one-shot instead of Tags2PartsTags2Parts weak supervision · Tags2Parts engineAUC: 0.46 -> 0.88Improved
use BAE-NET with 1 exemplar instead of PointNet++ on 10% dataPointNet++ · ShapeNet part 15 categoriesaverage IOU: 73.5 -> 76.6Improved
use BAE-NET with 3 exemplars instead of PointNet++ on 30% dataPointNet++ · ShapeNet part 15 categoriesaverage IOU: 76.6 -> 78.7Improved
reduce capacity and add regularization to supervised baselines (ablation)PointNet, PointNet++, PointCNN, SSCN · ShapeNet part 1-exemplar vs 10%average IOU: PointNet 72.1 -> 73.8; PointNet++ 73.5 -> 74.0; PointCNN 58.0 -> 58.6; SSCN 56.7 -> 57.8No clear effect

Later papers that compared with this method

3 later accepted papers report BAE-Net as a baseline in their results tables; 2 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