AI Paper Atlas

Research map / 3D vision / Face and shape

Generative 3D Part Assembly via Dynamic Graph Learning

jialei huang, Guanqi Zhan, Qingnan Fan, Kaichun Mo, Lin Shao, Baoquan Chen, Leonidas Guibas, Hao Dong

NeurIPS 2020 · 3D vision › Face and shape · approach: 3D shape generative modeling · 49 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
replace per-part MLP with iterative graph learning (ablation)backbone · PartNet TablePart accuracy: 26.05 -> 42.09Improved
add dynamic relation reasoning to backbone (ablation)backbone · PartNet TablePart accuracy: 42.09 -> 46.85Improved
add dynamic part aggregation to backbone (ablation)backbone · PartNet TablePart accuracy: 42.09 -> 48.01Improved
add both relation reasoning and part aggregation (ablation)backbone · PartNet TablePart accuracy: 42.09 -> 49.51Improved
learn relation weights instead of static GT adjacency (ablation)full model · PartNet TablePart accuracy: 45.43 -> 49.51Improved
reason relation from poses instead of transformed geometry (ablation)full model · PartNet TablePart accuracy: 45.11 -> 49.51Improved
swap order of dense and sparse node sets (ablation)full model · PartNet TablePart accuracy: 49.51 -> 49.19No clear effect
use max pooling instead of average pooling in aggregation (ablation)full model · PartNet TablePart accuracy: 48.92 -> 49.51Improved
use 5 GNN iterations instead of 3 or 7 (ablation)full model · PartNet TablePart accuracy: 45.51/49.51/44.6 for 3/5/7Mixed
add translation loss (ablation)full model · PartNet TablePart accuracy: 24.48 -> 49.51Improved
add rotation loss (ablation)full model · PartNet TablePart accuracy: 46.94 -> 49.51Improved
add shape loss (ablation)full model · PartNet TablePart accuracy: 48.23 -> 49.51Improved

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