AI Paper Atlas

Research map / 3D vision / Human pose estimation

PSVT: End-to-End Multi-Person 3D Pose and Shape Estimation With Progressive Video Transformers

Zhongwei Qiu, Qiansheng Yang, Jian Wang, Haocheng Feng, Junyu Han, Errui Ding, Chang Xu, Dongmei Fu, Jingdong Wang

CVPR 2023 · 3D vision › Human pose estimation · approach: Temporal video pose estimation · 38 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
use progressive decoding with PGA rather than Split-PoSh (ablation)PSVT · 3DPWPA-MPJPE: 46.9 -> 43.5Improved
use progressive decoding with PGA rather than Split-PoSh (ablation)PSVT · 3DPWMPJPE: 78.3 -> 73.1Improved
use progressive decoding with PGA rather than Split-PoSh (ablation)PSVT · 3DPWMPVE: 87.5 -> 84.0Improved
add PGA instead of a convolutional decoder (ablation)image-encoder PSVT · 3DPWPA-MPJPE: 49.8 -> 45.7Improved
add PGA instead of a convolutional decoder (ablation)image-encoder PSVT · 3DPWMPJPE: 86.2 -> 75.5Improved
add PGA instead of a convolutional decoder (ablation)image-encoder PSVT · 3DPWMPVE: 96.9 -> 84.9Improved
add a spatio-temporal encoder rather than a spatial encoder (ablation)PSVT with PGA · 3DPWPA-MPJPE: 45.7 -> 44.1Improved
add a spatio-temporal encoder rather than a spatial encoder (ablation)PSVT with PGA · 3DPWMPJPE: 75.5 -> 74.2Improved
add a spatio-temporal encoder rather than a spatial encoder (ablation)PSVT with PGA · 3DPWMPVE: 84.9 -> 84.5Improved
add Token Aligning to STSD (ablation)PSVT · 3DPWMPJPE: 76.6 -> 75.5Improved
add Window Pose Self-Attention to STSD (ablation)PSVT · 3DPWMPJPE: 77.1 -> 75.5Improved
add Window Shape Self-Attention to STSD (ablation)PSVT · 3DPWMPJPE: 76.1 -> 75.5Improved

Later papers that compared with this method

2 later accepted papers report PSVT as a baseline in their results tables; 2 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