AI Paper Atlas

Research map / 3D vision / Human pose estimation

SMPLer: Taming Transformers for Monocular 3D Human Shape and Pose Estimation

Xiangyu Xu, Lijuan Liu, Shuicheng Yan

TPAMI 2023 · 3D vision › Human pose estimation · approach: Transformer-based multi-view 3D pose · 22 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 multi-scale features (ablation)SMPLer · Human3.6MMPJPE: 48.3 -> 47.0Improved
use SMPL-based target with decoupled attention instead of full attention and vertex-based (ablation)Transformer · Human3.6MMPJPE: 51.9 -> 47.0Improved
use SMPL-based target instead of vertex-based (ablation)decoupled attention multi-scale · GPU memorymemory (G): 1.15 -> 0.44Improved
use decoupled instead of full attention (ablation)vertex-based multi-scale · GPU memorymemory (G): 7.3 -> 1.15Improved
use separate projections per scale instead of concatenation (ablation)SMPLer · Human3.6MMPJPE: 48.5 -> 47.0Improved
add feature positional encoding (ablation)SMPLer · Human3.6MMPJPE: 50.4 -> 47.0Improved
use pooling-based FPE instead of all-scale FPE (ablation)SMPLer · Human3.6MMPJPE: 49.0 -> 47.0Improved
add joint-aware attention (ablation)SMPLer · Human3.6MMPJPE: 51.4 -> 47.0Improved
add relative positional encoding eta (ablation)SMPLer · Human3.6MMPJPE: 48.7 -> 47.0Improved
increase Transformer blocks from 1 to 3 (ablation)SMPLer · Human3.6MMPJPE: 48.6 -> 47.0Improved
increase units per block from 1 to 2 (ablation)SMPLer · Human3.6MMPJPE: 48.5 -> 47.0Improved
increase units per block from 2 to 3 (ablation)SMPLer · Human3.6MMPJPE: 47.0 -> 47.1No clear effect

Later papers that compared with this method

1 later accepted paper reports SMPLer-X-L as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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