AI Paper Atlas

Research map / 3D vision / Human pose estimation

MeshMamba: State Space Models for Articulated 3D Mesh Generation and Reconstruction

Yusuke Yoshiyasu, Leyuan Sun, Ryusuke Sagawa

ICCV 2025 · 3D vision › Human pose estimation · approach: Human mesh recovery from images · 2 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 Mamba block instead of MLP (ablation)MambaDiff3D · Unconditional human generation (SURREAL test)1-NNA (%): 73.7 -> 53.1Improved
use Mamba block instead of GNN (ablation)MambaDiff3D · Unconditional human generation (SURREAL test)1-NNA (%): 74.2 -> 53.1Improved
use Mamba block instead of transformer (ablation)MambaDiff3D · Unconditional human generation (SURREAL test)1-NNA (%): 53.6 -> 53.1No clear effect
serialize by part-IUV instead of SMPL connectivity order (ablation)MambaDiff3D · Unconditional human generation (SURREAL test)1-NNA (%): 60.0 -> 54.4Improved
use seven part-IUV serializations instead of one (ablation)MambaDiff3D · Unconditional human generation (SURREAL test)1-NNA (%): 54.4 -> 53.0Improved
combine SMPL and XYZ serialization instead of SMPL connectivity alone (ablation)MambaDiff3D · Unconditional human generation (SURREAL test)1-NNA (%): 60.0 -> 53.1Improved
use six XYZ serializations instead of one alongside SMPL (ablation)MambaDiff3D · Unconditional human generation (SURREAL test)1-NNA (%): 53.1 -> 53.5No clear effect
use random vertex ordering (ablation)MeshMamba · Unconditional generationtrainingHurt
replace Mamba with transformer in diffusion layers (inference speed, 10475 vertices, A100, 250 DDIM steps) (ablation)MambaDiff3D · Mesh generation speedgeneration time: 28.1 sec -> 4.5 secImproved
replace Mamba with transformer (V100 generation time) (ablation)MambaDiff3D · Mesh generation speedgeneration time: 58.3 sec -> 6.6 secImproved
replace Mamba with transformer (training time, 6890 tokens) (ablation)MeshMamba · Training speedtime per epoch: 100 minutes -> 18 minImproved
fine-tune on UBody (ablation)Mamba-HMR · UBody whole-body mesh recoveryPA-MVE All (mm): 26.3 -> 25.9Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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