AI Paper Atlas

Research map / Point clouds / Shape and surface completion

AdaCoSeg: Adaptive Shape Co-Segmentation With Group Consistency Loss

Chenyang Zhu, Kai Xu, Siddhartha Chaudhuri, Li Yi, Leonidas J. Guibas, Hao Zhang

CVPR 2020 · Point clouds › Shape and surface completion · approach: Unsupervised shape correspondence · 37 citations (OpenAlex)

Check 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 AdaCoSeg instead of Shushape co-segmentation · COSEG ChairRand Index: 0.076 -> 0.055Improved
use AdaCoSeg instead of Shushape co-segmentation · COSEG LampRand Index: 0.069 -> 0.059Improved
use AdaCoSeg instead of Sidishape co-segmentation · COSEG VaseRand Index: 0.102 -> 0.189Hurt
use AdaCoSeg instead of Shushape co-segmentation · COSEG GuitarRand Index: 0.041 -> 0.032Improved
apply AdaCoSeg to the initially segmented training shapesthe training-data segmentations · Training-data ChairRand Index: 0.21 -> 0.09Improved
apply AdaCoSeg to the initially segmented training shapesthe training-data segmentations · Training-data TableRand Index: 0.27 -> 0.14Improved
apply AdaCoSeg to the initially segmented training shapesthe training-data segmentations · Training-data BicycleRand Index: 0.31 -> 0.22Improved
apply AdaCoSeg to the initially segmented training shapesthe training-data segmentations · Training-data LampRand Index: 0.18 -> 0.16Improved
apply AdaCoSeg to the initially segmented training shapesthe training-data segmentations · Training-data CarRand Index: 0.38 -> 0.27Improved
apply AdaCoSeg to the initially segmented training shapesthe training-data segmentations · Training-data PlaneRand Index: 0.24 -> 0.13Improved
add the part prior network (ablation)AdaCoSeg · shape co-segmentationgroup consistency loss decreaseImproved
add random noise when training the part prior (ablation)AdaCoSeg · shape co-segmentationtraining effectivenessImproved

Later papers that compared with this method

2 later accepted papers report AdaCoSeg as a baseline in their results tables; 2 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