AI Paper Atlas

Research map / 3D vision / 3D generation

UniPart: Part-Level 3D Generation with Unified 3D Geom-Seg Latents

Xufan He, Yushuang Wu, Xiaoyang Guo, Chongjie Ye, Jiaqing Zhou, Tianlei Hu, Xiaoguang Han, Dong Du

CVPR 2026 · 3D vision › 3D generation · approach: Text-to-3D scene generation · 8 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 segmentation information to the VecSet latent space (Geom-Seg VecSet VAE) (ablation)Hunyuan3D-2.1 VAE · VAE reconstructionChamfer Distance (x10^4): 1.29 -> 1.30No clear effect
generate part latents in a normalized canonical space (dual-space generation) (ablation)UniPart part-level DiT · Part-level generation (qualitative)part geometric fidelityImproved
add local attention alongside global attention (ablation)UniPart part-level DiT · Part-level generation (qualitative)part cohesion and global consistencyImproved
add learnable space embedding to distinguish gcs and ncs tokens (ablation)UniPart part-level DiT · Part-level generation (qualitative)assembly successImproved
UniPart vs X-Part on Chamfer Distancepart-level generation · Part-level generation geometry qualityChamfer Distance (x10^2): 0.82 -> 0.72Improved
UniPart vs X-Part on F1@0.1part-level generation · Part-level generation geometry qualityF1@0.1 (x10^2): 88.90 -> 92.21Improved
UniPart vs X-Part on IoUpart-level generation · Part-level generation geometry qualityIoU (x10^2): 31.95 -> 21.99Hurt
joint geometry and segmentation generation on structurally complex inputsUniPart whole-level DiT · Failure casesoutput validityHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 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