AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

BrepVGAE: Variational Graph Autoencoder with Unified Latent Representation for B-rep

Hao Guo, Liyuan Deng, Yongkang Dai, Ruohan Wang, Jiahao Li, Yunpeng Bai, Yilei Shi

CVPR 2026 · Graph learning › Graph self-supervised learning · approach: Semi-supervised node representation learning

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 SparseGNN instead of GAT (ablation)BrepVGAE encoder · DeepCAD generation (60K ablation)COV: 60.46 -> 78.75Improved
use SparseGNN instead of GCN (ablation)BrepVGAE encoder · DeepCAD generation (60K ablation)COV: 68.78 -> 78.75Improved
use SparseGNN instead of GCN (ablation)BrepVGAE encoder · DeepCAD generation (60K ablation)MMD: 1.18 -> 1.18No clear effect
use multi-slot learnable queries with KV expansion vs single query (ablation)set decoder · DeepCAD generation (60K ablation)COV: 65.30 -> 78.75Improved
add key-value expansion (ablation)set decoder · DeepCAD generation (60K ablation)COV: 70.25 -> 78.75Improved
make queries learnable vs fixed (ablation)set decoder · DeepCAD generation (60K ablation)COV: 63.53 -> 78.75Improved
two-stage training vs end-to-end (ablation)BrepVGAE · DeepCAD generation (60K ablation)COV: 60.20 -> 78.75Improved
two-stage training vs frozen geometry throughout (ablation)BrepVGAE · DeepCAD generation (60K ablation)COV: 76.35 -> 78.75Improved
add CD loss to edge autoencoder (ablation)Edge VAE · Edge point cloud AECD: 0.987 -> 0.658Improved
add CD loss to face autoencoder (ablation)Face VAE · Surface point cloud AECD: 1.126 -> 0.619Improved
Hungarian vs nearest-neighbor matchingOurs · DeepCAD generationCOV: 73.40 -> 79.82Improved
Hungarian vs Sinkhorn matchingOurs · DeepCAD generationCOV: 78.71 -> 79.82Improved

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