AI Paper Atlas

Research map / 3D vision / Face and shape

Unsupervised Primitive Discovery for Improved 3D Generative Modeling

Salman H. Khan, Yulan Guo, Munawar Hayat, Nick Barnes

CVPR 2019 · 3D vision › Face and shape · approach: 3D shape generative modeling · 38 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
factorize shape generation into primitive generation followed by 3D shape refinementPrimitive GAN · ModelNet10accuracyImproved
factorize shape generation using primitive representationsPrimitive GAN · IKEAAP: 55.0 -> 60.4Improved
add volumetric occupancy cost (ablation)primitive discovery CRF · ModelNet10recall: 72.8 -> 83.0Improved
add shape uniformity cost (ablation)primitive discovery CRF · ModelNet10recall: 81.5 -> 83.0Improved
add primitive compactness cost (ablation)primitive discovery CRF · ModelNet10recall: 77.2 -> 83.0Improved
add support cost (ablation)primitive discovery CRF · ModelNet10recall: 82.9 -> 83.0Improved
add shape symmetry cost (ablation)primitive discovery CRF · ModelNet10recall: 80.0 -> 83.0Improved
use pairwise and higher-order CRF potentials in addition to unary costs (ablation)primitive discovery CRF · ModelNet10recall: 51.6 -> 83.0Improved

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