AI Paper Atlas

Research map / 3D vision / Human pose estimation

UPose3D: Uncertainty-Aware 3D Human Pose Estimation with Cross-View and Temporal Cues

Vandad Davoodnia, Saeed Ghorbani, Marc-André Carbonneau, Alexandre Messier, Ali Etemad

ECCV 2024 · 3D vision › Human pose estimation · approach: Transformer-based multi-view 3D pose · 8 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 pose compiler (cross-view and temporal refinement) (ablation)UPose3D · Human3.6mMPJPE (mm): 37.14 -> 26.42Improved
keep the original 2D image-branch predictions in the final estimate (ablation)UPose3D · Human3.6mMPJPE (mm): 69.90 -> 26.42Improved
add uncertainty modeling to both branches (normalizing flows) (ablation)UPose3D · Human3.6mMPJPE (mm): 48.11 -> 26.42Improved
add uncertainty to the pose compiler at inference only (ablation)UPose3D · Human3.6mMPJPE (mm): 26.42 -> 26.42 (PA-MPJPE 23.58 -> 23.42)No clear effect
add image-branch uncertainty (ablation)UPose3D · Human3.6mMPJPE (mm): 27.61 -> 26.42Improved
extend temporal window from 1 to 27 frames (ablation)UPose3D · Human3.6mMPJPE (mm): 26.9 -> 26.4Improved
extend temporal window to 243 frames (ablation)UPose3D · Human3.6mMPJPE (mm): 26.42 -> 33.17Hurt
use criss-cross attention instead of full attention (ablation)spatiotemporal encoder · Human3.6m (T=243)MPJPE (mm): 34.97 -> 33.17Improved
use DLT initialization instead of zero initialization (ablation)3D keypoint MLE · Human3.6mMPJPE (mm): 28.51 -> 26.42Improved
append epipolar line or relative camera position to point cloud inputs (ablation)pose compiler · Human3.6mMPJPE (mm): 26.42 -> 26.46 (epipolar line), 26.37 (camera pos.)No clear effect
train on synthetic multi-view AMASS data and apply to unseen RICH environmentUPose3D · RICH (OoD)MPJPE (mm): 66.0 -> 36.2 (vs HRNet-W48 + DLT)Improved

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