AI Paper Atlas

Research map / 3D vision / Human pose estimation

EgoBody: Human Body Shape and Motion of Interacting People from Head-Mounted Devices

Siwei Zhang, Qianli Ma, Yan Zhang, Zhiyin Qian, Taein Kwon, Marc Pollefeys, Federica Bogo, Siyu Tang

ECCV 2022 · 3D vision › Human pose estimation · approach: Physics and sensor-based motion capture · 104 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
fine-tune on EgoBody training setSPIN · EgoBody test setMPJPE: 182.8 -> 106.5Improved
fine-tune on EgoBody training setMETRO · EgoBody test setMPJPE: 153.1 -> 98.5Improved
fine-tune on EgoBody training setEFT · EgoBody test setMPJPE: 123.9 -> 102.1Improved
fine-tune on EgoBody training setSPIN · You2MePA-MPJPE: 152.8 -> 87.9Improved
fine-tune on EgoBody training setEFT · You2MePA-MPJPE: 95.8 -> 85.6Improved
fine-tune on EgoBody training setMETRO · You2MePA-MPJPE: 117.7 -> 88.2Improved
fine-tune on EgoBody training set (robustness to blur)SPIN · EgoBody test setstd over sharpness levels: 27.3 to 2.4Improved
fine-tune on EgoBody training set (robustness to blur)EFT · EgoBody test setstd over sharpness levels: 11.1 to 1.3Improved
add motion blur augmentation when fine-tuning on original data (ablation)SPIN · EgoBody test setMPJPE: 182.8 -> 184.9Hurt
add aggressive crop augmentation / pretraining (EFT vs SPIN)SPIN-architecture · EgoBody test setMPJPE: 182.8 -> 123.9Improved
egocentric images versus third-person (3DPW) testSoTA 3DHPS methods · EgoBody vs 3DPW3D joint error: 77% higherHurt
heavy motion blur (sharpness < 10)SoTA 3DHPS methods · EgoBody test setMPJPEHurt

Later papers that compared with this method

1 later accepted paper reports Egobody3M as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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