AI Paper Atlas

Research map / 3D vision / Human pose estimation

AJAHR: Amputated Joint Aware 3D Human Mesh Recovery

Hyunjin Cho, Giyun Choi, Jongwon Choi

ICCV 2025 · 3D vision › Human pose estimation · approach: Human mesh recovery from images · 3 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 tokenizer switching between amputee and non-amputee codebooks (versus amputation-only tokenizer) (ablation)AJAHR · ITW-amputeeMPJPE (mm): 131.12 -> 129.25Improved
add tokenizer switching (versus non-amputation-only tokenizer) (ablation)AJAHR · ITW-amputeeMPJPE (mm): 134.71 -> 129.25Improved
add tokenizer switching (versus non-amputation-only tokenizer) (ablation)AJAHR · A3DMPJPE (mm): 76.31 -> 73.19Improved
add keypoint heatmaps to image input of BPAC-Net (ablation)AJAHR · ITW-amputeeMPJPE (mm): 154.55 -> 129.25Improved
add image to keypoint-only input (ablation)AJAHR · ITW-amputeeMPJPE (mm): 146.21 -> 129.25Improved
add Gaussian noise to input keypoints (100% noise ratio) (ablation)AJAHR · ITW-amputeeMPJPE (mm): 143.74 -> 147.41Hurt
use 320 tokens instead of 640 tokens (ablation)AJAHR-Tokenizer · ITW-amputeeMPJPE (mm): 151.80 -> 129.25Improved
use 320 tokens instead of 160 tokens (ablation)AJAHR-Tokenizer · ITW-amputeeMPJPE (mm): 147.91 -> 129.25Improved
add BPAC-Net to weak baseline HMR2.0 (ablation)HMR2.0 · ITW-amputeeMPJPE (mm): 154.43 -> 176.46Hurt
train on amputee data with AJAHR instead of TokenHMRAJAHR vs TokenHMR · ITW-amputeeMPJPE (mm): 146.12 -> 129.25Improved
use AJAHR on non-amputee data versus TokenHMRAJAHR vs TokenHMR · 3DPWPA-MPJPE (mm): 47.17 -> 44.94Improved
use AJAHR on 3DPW versus TokenHMR (MVE)AJAHR vs TokenHMR · 3DPWMVE (mm): 90.23 -> 95.26Hurt

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