AI Paper Atlas

Research map / Point clouds / Shape and surface completion

PartDiffuser: Part-wise 3D Mesh Generation via Discrete Diffusion

Yichen Yang, Hong Li, Haodong Zhu, Linin Yang, Guojun Lei, Sheng Xu, Baochang Zhang

CVPR 2026 · Point clouds › Shape and surface completion · approach: Point cloud diffusion generation · 7 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 part-specific conditioning to global-only conditioning (ablation)PartDiffuser · ObjaverseCD x10^3: 29.125 -> 17.813Improved
add global conditioning to parts-only conditioning (ablation)PartDiffuser · ObjaverseCD x10^3: 54.728 -> 17.813Improved
add part-specific conditioning to global-only conditioning (ablation)PartDiffuser · ObjaverseF1: 0.281 -> 0.343Improved
add global conditioning to parts-only conditioning (ablation)PartDiffuser · ObjaverseF1: 0.239 -> 0.343Improved
increase sampling acceleration factor from k=1 to k=2 (steps 1024 to 512) (ablation)PartDiffuser · ObjaverseCD x10^3: 17.813 -> 27.657Hurt
increase sampling acceleration factor from k=1 to k=4 (steps 1024 to 256) (ablation)PartDiffuser · ObjaverseCD x10^3: 17.813 -> 44.720Hurt
increase sampling acceleration factor from k=1 to k=4 (ablation)PartDiffuser · Objaverseinference time (s): 63.8 -> 17.1Improved
part-wise semi-autoregressive diffusion vs MeshAnythingV2PartDiffuser · ObjaverseCD x10^3: 24.402 -> 17.813Improved
part-wise diffusion vs TreeMeshGPTPartDiffuser · HSSDCD x10^3: 4.522 -> 5.364Mixed
part-wise diffusion vs TreeMeshGPTPartDiffuser · 3DFrontF1: 0.462 -> 0.453Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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