AI Paper Atlas

Research map / 3D vision / Face and shape

MeshLLM: Empowering Large Language Models to Progressively Understand and Generate 3D Mesh

Shuangkang Fang, I-Chao Shen, Yufeng Wang, Yi-Hsuan Tsai, Yi Yang, Shuchang Zhou, Wenrui Ding, Takeo Igarashi, Ming-Hsuan Yang

ICCV 2025 · 3D vision › Face and shape · approach: 3D shape generative modeling · 13 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 KNN-based Primitive-Mesh data (ablation)MeshLLM · ShapeNet chair generationFID: 49.33 -> 42.39Improved
add KNN-based Primitive-Mesh data (ablation)MeshLLM · Objaverse-XL mesh understandingCIDEr: 0.921 -> 1.753Improved
add semantic-based Primitive-Mesh data (ablation)MeshLLM · ShapeNet chair generationFID: 52.76 -> 42.39Improved
add semantic-based Primitive-Mesh data (ablation)MeshLLM · Objaverse-XL mesh understandingCIDEr: 0.782 -> 1.753Improved
add vertex-to-face prediction task (ablation)MeshLLM · ShapeNet chair generationFID: 48.68 -> 42.39Improved
add vertex-to-face prediction task (ablation)MeshLLM · Objaverse-XL mesh understandingCIDEr: 1.229 -> 1.753Improved
add mesh assembly task (ablation)MeshLLM · ShapeNet chair generationFID: 54.26 -> 42.39Improved
add mesh assembly task (ablation)MeshLLM · Objaverse-XL mesh understandingCIDEr: 0.894 -> 1.753Improved
train KNN PM first then semantic PM instead of reverse order (ablation)MeshLLM · ShapeNet chair generationFID: 45.77 -> 42.39Improved
train KNN PM first then semantic PM instead of reverse order (ablation)MeshLLM · Objaverse-XL mesh understandingCIDEr: 1.303 -> 1.753Improved
MeshLLM vs LLaMA-Mesh baseline (Primitive-Mesh data and progressive tasks)LLaMA-3.1-8B-Instruct · ShapeNet chair generationCOV: 19.53 -> 47.33Improved
MeshLLM vs MeshXL encoder-based generatorMeshLLM · ShapeNet chair generationFID: 40.33 vs 42.39No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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