AI Paper Atlas

Research map / 3D vision / Human pose estimation

Learning 3D Human Shape and Pose from Dense Body Parts

Hongwen Zhang, Jie Cao, Guo Lu, Wanli Ouyang, Zhenan Sun

TPAMI 2020 · 3D vision › Human pose estimation · approach: Human shape and pose regression

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 IUV maps instead of conv features as intermediate representation (ablation)baseline network · Human3.6MPVE (mm): 98.9 -> 87.8Improved
use IUV maps instead of part segmentation (ablation)baseline network · Human3.6MPVE (mm): 90.4 -> 87.8Improved
add decomposed multi-stream perception (D-Net) (ablation)baseline network · Human3.6MPVE (mm): 87.8 -> 74.3Improved
add decomposed perception (ablation)baseline network · Human3.6MPVE-S (mm): 38.0 -> 36.3No clear effect
use scale ratios alpha_k instead of equal scales 0.5 (ablation)D-Net · Human3.6MPVE (mm): 76.1 -> 74.3Improved
use partial IUV maps instead of all body parts (ablation)D-Net · Human3.6MPVE (mm): 76.8 -> 74.3Improved
add aggregated refinement (position-aided) (ablation)DaNet · Human3.6MPVE (mm): 71.7 -> 66.5Improved
use position-aided instead of direct refinement (ablation)DaNet · Human3.6MMPJPE-PA (mm): 45.5 -> 42.9Improved
replace LSTM aggregation with graph-based aggregation (ablation)DaNet · COCO valAP50: 58.7 -> 65.5Improved
add PartDrop to DaNet-GCN (ablation)DaNet · COCO valAP: 31.9 -> 33.8Improved
add Dropout instead of PartDrop (ablation)DaNet-GCN · COCO valAP: 31.9 -> 30.6Hurt
add DropBlock instead of PartDrop (ablation)DaNet-GCN · COCO valAP: 31.9 -> 32.0No clear effect

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