AI Paper Atlas

Research map / 3D vision / Human pose estimation

DeciWatch: A Simple Baseline for 10× Efficient 2D and 3D Pose Estimation

Ailing Zeng, Xuan Ju, Lei Yang, Ruiyuan Gao, Xizhou Zhu, Bo Dai, Qiang Xu

ECCV 2022 · 3D vision › Human pose estimation · approach: Transformer-based multi-view 3D pose

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 DenoiseNet (ablation)DeciWatch · 3DPW (PARE)MPJPE: 79.8 -> 77.2Improved
use Transformer DenoiseNet instead of TCNs (ablation)DeciWatch · 3DPW (PARE)MPJPE: 80.5 -> 77.2Improved
use Transformer DenoiseNet instead of MLPs (ablation)DeciWatch · 3DPW (PARE)MPJPE: 79.5 -> 77.2Improved
use Transformer RecoverNet instead of linear interpolation (ablation)DeciWatch · 3DPW (PARE)MPJPE: 79.8 -> 77.2Improved
use Transformer RecoverNet instead of TCNs (ablation)DeciWatch · 3DPW (PARE)MPJPE: 172.3 -> 77.2Improved
add MLPs at the last layer of TCN recovery (ablation)TCN RecoverNet · 3DPW (PARE)MPJPE: 172.3 -> 99.5Improved
use Transformer RecoverNet instead of MLPs (ablation)DeciWatch · 3DPW (PARE)MPJPE: 78.0 -> 77.2Improved
lower sampling ratio from 100% to about 20% (ablation)DeciWatch · 3DPW (PARE)MPJPE: 78.9 -> 75.0Improved
lower sampling ratio below 8% (N above 12) (ablation)DeciWatch · 3DPW (PARE)MPJPE: 75.0 -> 85.3Hurt
vary input window size 11 to 201 (ablation)DeciWatch · 3DPWMPJPENo clear effect
vary loss weight lambda from 1 to 10 (ablation)DeciWatch · 3DPW (PARE)MPJPE: 78.0 -> 77.2No clear effect
use DeciWatch recovery instead of cubic spline at interval 10DeciWatch · Human3.6M labelingMPJPE: 5.36 -> 2.89Improved

Later papers that compared with this method

1 later accepted paper reports DeciWatch 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