AI Paper Atlas

Research map / 3D vision / Human pose estimation

Divide and Fuse: Body Part Mesh Recovery from Partially Visible Human Images

Tianyu Luan, Zhongpai Gao, Luyuan Xie, Abhishek Sharma, Hao Ding, Benjamin Planche, Meng Zheng, Ange Lou, Terrence Chen, Junsong Yuan, Ziyan Wu

ECCV 2024 · 3D vision › Human pose estimation · approach: Human mesh recovery from images · 4 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 6D rotation loss on HPPM part rotations (ablation)D&F · PV-Human3.6M (finetuned)MPVE (mm): 95.6 -> 63.3Improved
add overlapping loss between adjacent parts (ablation)D&F · PV-Human3.6M (finetuned)MPVE (mm): 74.5 -> 63.3Improved
add translation loss on part global translation (ablation)D&F · PV-Human3.6M (finetuned)MPVE (mm): 75.1 -> 63.3Improved
add part 3D per-vertex loss (ablation)D&F · PV-3DPW (finetuned)MPVE (mm): 120.2 -> 109.9Improved
add depth consistency loss (ablation)D&F · PV-Human3.6M (finetuned)MPVE (mm): 65.4 -> 63.3Improved
add part 2D projection loss (ablation)D&F · PV-Human3.6M (finetuned)MPVE (mm): 64.2 -> 63.3Improved
use adjustable number of shape parameters per part instead of fixed 24 per part (ablation)D&F · PV-Human3.6M (finetuned)MPVE (mm): 67.5 -> 63.3Improved
add partially visible augmentation finetuningD&F · PV-Human3.6MMPVE (mm): 155.7 -> 63.3Improved
replace top-down SMPL-based methods with bottom-up part-based D&Fpartially visible human mesh recovery · PV-3DPW (directly tested)MPVE (mm): 268.2 -> 208.6Improved
increase number of visible parts from 1-4 to 5-10D&F · PV-3DPWMPVE (mm): 109.9 -> 117.4Mixed
apply D&F to full-body visible inputs without modificationD&F · 3DPW (full-body visible)MPJPE (mm): 100.5 vs VIBE 93.5Mixed

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