AI Paper Atlas

Research map / Point clouds / Shape and surface completion

Rethinking 3D Shape Generation: Diffusion over Superquadrics

Zhiyang Liu, Li Wanze, Yuwei Wu, Chengran Yuan, JIAWEI SUN, Rui Zheng, Marcelo H Ang Jr

ICML 2026 · Point clouds › Shape and surface completion · approach: Point cloud diffusion generation · 0 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 existence token (ablation)DoSs · ShapeNet Chair1-NNA@CD: 93.32 -> 58.36Improved
add existence token (ablation)DoSs · ShapeNet ChairCOV@CD: 19.91 -> 48.41Improved
add 6D rotation representation instead of Euler angles (ablation)DoSs · ShapeNet Chair1-NNA@CD: 58.36 -> 57.57Improved
add 6D rotation representation instead of Euler angles (ablation)DoSs · ShapeNet ChairCOV@CD: 48.41 -> 50.37Improved
sort primitives by y-position instead of random order (ablation)DoSs · ShapeNet Chair1-NNA@CD: 57.57 -> 55.28Improved
sort primitives by y-position instead of random order (ablation)DoSs · ShapeNet ChairCOV@CD: 50.37 -> 50.93Improved
sort primitives by volume instead of random order (ablation)DoSs · ShapeNet Chair1-NNA@CD: 57.57 -> 53.80Improved
sort primitives by volume instead of random order (ablation)DoSs · ShapeNet ChairCOV@CD: 50.37 -> 51.31Improved
train one multi-class model instead of category-specific modelsDoSs · ShapeNet Chair1-NNA@CD: 53.80 -> 55.70No clear effect
train one multi-class model instead of category-specific modelsDoSs · ShapeNet Airplane1-NNA@CD: 61.92 -> 60.20Improved
train one multi-class model instead of category-specific modelsDoSs · ShapeNet Car1-NNA@CD: 57.50 -> 61.11Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 3 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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