AI Paper Atlas

Research map / 3D vision / Face and shape

Self-supervised Learning of Hybrid Part-aware 3D Representations of 2D Gaussians and Superquadrics

Zhirui Gao, Renjiao Yi, Yuhang Huang, Wei Chen, Chenyang Zhu, Kai Xu

ICCV 2025 · 3D vision › Face and shape · approach: Single-view 3D reconstruction · 13 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 opacity loss (ablation)Ours (Block-level) · ShapeNet chair ablationChamfer distance: 5.72 -> 2.32Improved
add coverage loss (ablation)Ours (Block-level) · ShapeNet chair ablationChamfer distance: 3.21 -> 2.32Improved
add adaptive strategy (ablation)Ours (Block-level) · ShapeNet chair ablationChamfer distance: 3.16 -> 2.32Improved
add overlap loss (ablation)Ours (Block-level) · ShapeNet chair ablationChamfer distance: 2.11 -> 2.32Hurt
add parsimony loss (ablation)Ours (Block-level) · ShapeNet chair ablationChamfer distance: 1.91 -> 2.32Hurt
add parsimony loss (ablation)Ours (Block-level) · ShapeNet chair ablationnumber of primitives: 10.1 -> 6.6Improved
add overlap loss (ablation)Ours (Point-level) · ShapeNet chair ablationChamfer distance: 1.34 -> 0.94Improved
increase parsimony weight from 0.01 to 0.1 (ablation)Ours (Block-level) · DTUChamfer distance: 4.19 -> 6.46Hurt
increase initial primitives M from 4 to 16 (ablation)Ours (Block-level) · DTUChamfer distance: 4.97 -> 3.99Improved
increase initial primitives M from 8 to 16 (ablation)Ours (Point-level) · DTUChamfer distance: 1.05 -> 1.07No clear effect
use point-level instead of block-level representationOurs · DTUChamfer distance: 4.19 -> 0.98Improved
use hybrid Gaussians+superquadrics instead of DBWDBW · DTUChamfer distance: 4.76 -> 0.98Improved

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