AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

MeshMosaic: Scaling Artist Mesh Generation via Local-to-Global Assembly

Rui Xu, Tianyang Xue, Qiujie Dong, Le Wan, Zhe Zhu, Peng Li, Zhiyang Dou, Cheng Lin, Shiqing Xin, Yuan Liu, Wenping Wang, Taku Komura

CVPR 2026 · Image generation › Autoregressive and latent generation · approach: Generative latent space tooling

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
segment shapes into patches with local quantization and boundary-conditioned autoregressive generationMeshMosaic vs DeepMesh · ObjaverseF-score: 0.471 -> 0.785Improved
segment into patches with local quantization and boundary conditioningMeshMosaic vs DeepMesh · Thingi10KHausdorff distance: 0.165 -> 0.051Improved
segment into patches with local quantization and boundary conditioningMeshMosaic vs BPT · ShapeNetHausdorff distance: 0.017 -> 0.037Hurt
segment into patches with local quantization and boundary conditioningMeshMosaic vs BPT · ShapeNetChamfer distance L2 x10^3: 0.012 -> 0.019Hurt
segment into patches with local quantization and boundary conditioningMeshMosaic vs BPT · ShapeNetEdge Chamfer distance: 0.040 -> 0.052Hurt
segment into patches with local quantization and boundary conditioningMeshMosaic vs DeepMesh · ShapeNetHausdorff distance: 0.037 -> 0.037No clear effect
segment into patches with local quantization and boundary conditioningMeshMosaic vs DeepMesh · ShapeNetF-score: 0.791 -> 0.929Improved
segment into patches with local quantization and boundary conditioningMeshMosaic vs BPT · ObjaverseEdge F-score: 0.164 -> 0.348Improved
segment into patches with local quantization and boundary conditioningMeshMosaic vs BPT · Thingi10KF-score: 0.496 -> 0.746Improved
segment into patches with local quantization and boundary conditioningMeshMosaic vs BPT · User studyDetail Recovery score: 1.084 -> 2.912Improved
segment into patches with local quantization and boundary conditioningMeshMosaic vs BPT · User studyNeatness score: 1.040 -> 2.780Improved
segment into patches with local quantization and boundary conditioningMeshMosaic vs DeepMesh · Complex fighter jet modeltriangle count: nearly 30K triangles vs a few hundred to a few thousandImproved

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