AI Paper Atlas

Research map / 3D vision / Human pose estimation

RePOSE: 3D Human Pose Estimation via Spatio-Temporal Depth Relational Consistency

Ziming Sun, Yuan Liang, Zejun Ma, Tianle Zhang, Linchao Bao, Guiqing Li, Shengfeng He

ECCV 2024 · 3D vision › Human pose estimation · approach: Monocular 2D-to-3D pose lifting · 12 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 spatial relational depth ranking loss (ablation)RePOSE baseline · Human3.6MMPJPE (mm): 37.9 -> 36.9Improved
add temporal relational depth ranking loss (ablation)RePOSE baseline · Human3.6MMPJPE (mm): 37.9 -> 37.2Improved
add both spatial and temporal losses (ablation)RePOSE baseline · Human3.6MMPJPE (mm): 37.9 -> 36.5Improved
add both spatial and temporal losses (ablation)RePOSE baseline · Human3.6MPA-MPJPE (mm): 32.5 -> 30.7Improved
fine-tune MotionBERT with the ST relational lossesMotionBERT · Human3.6MMPJPE (mm): 37.5 -> 36.7Improved
fine-tune STCFormer with the ST relational lossesSTCFormer · Human3.6MMPJPE (mm): 44.1 -> 43.3Improved
fine-tune P-STMO-S with the ST relational lossesP-STMO-S · Human3.6MMPJPE (mm): 46.1 -> 44.7Improved
RePOSE versus best prior on MPI-INF-3DHP PCKRePOSE · MPI-INF-3DHPPCK: 98.7 vs 98.3Mixed

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