AI Paper Atlas

Research map / Point clouds / Shape and surface completion

Unsupervised Learning of Category-Specific Symmetric 3D Keypoints from Point Sets

Clara Fernandez-Labrador, Ajad Chhatkuli, Danda Pani Paudel, Jose J. Guerrero, Cédric Demonceaux, Luc Van Gool

ECCV 2020 · Point clouds › Shape and surface completion · approach: Unsupervised shape correspondence · 40 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 category-specific symmetric linear basis keypoint model instead of per-category USIP baselinesymmetric linear basis keypoint network · 8 categoriescoverage: 29.4% more coverage on averageImproved
use symmetric linear basis model instead of USIP baselinesymmetric linear basis keypoint network · 8 categoriesinclusivity: ~95% vs ~89% on averageMixed
use ordered keypoints from the non-rigid basis model instead of USIP baselinesymmetric linear basis keypoint network · 8 categoriescorrespondence: 100 vs 30.11 to 55.6Improved
add instance-wise or basis symmetry modelling during training (ablation)symmetric linear basis keypoint network · chair, 10 keypoints, +-45 degree misalignmentrelative rotation errorImproved
train with Chamfer loss instead of l2 loss between nodes and keypoints (ablation)symmetric linear basis keypoint network · keypoint learningconvergenceImproved
vary the number of shape basis K between 5 and 10 (ablation)symmetric linear basis keypoint network · keypoint learningkeypoint qualityNo clear effect
approximate volume with 3D bounding box in coverage loss (ablation)symmetric linear basis keypoint network · keypoint learningperformanceNo clear effect
learn a common category rotation tied to the symmetry plane (ablation)symmetric linear basis keypoint network · misaligned point cloudsrotation ambiguityImproved

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