AI Paper Atlas

Research map / 3D vision / Face and shape

GetMesh: A Controllable Model for High-quality Mesh Generation and Manipulation

Ben Fei, Jinyi Wang, Lei Bai, K. J. Ray Liu, Xudong Xu, Weidong Yang, Ya Zhang, Ying He, Dahua Lin, Zhaoyang Lyu, Bo Dai

TPAMI 2025 · 3D vision › Face and shape · approach: Textured mesh 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
use 32-64 latent points instead of 128-256 (ablation)GetMesh · ShapeNet AirplaneShading-FID: 32.10 -> 206.57Hurt
use 2048-4096 latent points instead of 128-256 (ablation)GetMesh · ShapeNet AirplaneShading-FID: 32.10 -> 237.36Hurt
use 512-1024 latent points instead of 128-256 (ablation)GetMesh · ShapeNetShading-FID: 32.10 -> 44.32 (Airplane), 121.42 -> 113.22 (Car)Mixed
use 2048-4096 latent points instead of 128-256 (ablation)GetMesh · ShapeNet AirplaneCoverage (CD) percent: 47.6 -> 2.4Hurt
add refinement module to mesh autoencoder (ablation)GetMesh autoencoder · ShapeNet testMask IoU: 0.961 -> 0.968Improved
add refinement module to mesh autoencoder (ablation)GetMesh autoencoder · ShapeNet testChamfer distance x1e-3: 1.46 -> 1.34Improved
use 512-1024 latent points in autoencoder instead of 128-256 (ablation)GetMesh autoencoder · ShapeNet testChamfer distance x1e-3: 1.34 -> 1.07Improved
use 512-1024 latent points instead of 128-256 (ablation)GetMesh · ShapeNet generationseconds per sample: 1.17 -> 8.14Hurt
use 2048-4096 latent points instead of 128-256 (ablation)GetMesh · ShapeNet generationseconds per sample: 1.17 -> 92.18Hurt
use compact latent points for diffusion instead of 512 vectorsGetMesh vs 3DShape2VecSet · ShapeNet generationseconds per sample: 6.56 -> 1.17Improved
use GetMesh instead of 3DShape2VecSetmulti-category generation · ShapeNetShading-FID: 23.90 -> 16.50 (Table), 101.38 -> 121.42 (Car)Mixed
use GetMesh instead of 3DShape2VecSetmulti-category generation · ShapeNet Chair1-NNA (CD) percent: 60.66 -> 52.05Improved

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