AI Paper Atlas

Research map / 3D vision / Human pose estimation

AdaFuse: Adaptive Multiview Fusion for Accurate Human Pose Estimation in the Wild

Zhe Zhang, Chunyu Wang, Weichao Qiu, Wenhu Qin, Wenjun Zeng

IJCV 2020 · 3D vision › Human pose estimation · approach: Transformer-based multi-view 3D pose · 123 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 multiview heatmap fusion (HeuristicFuse)NoFuse · Human3.6M3D MPJPE (mm): 22.9 -> 21.0Improved
add adaptive fusion weights from appearance and geometry (AdaFuse)HeuristicFuse · Human3.6M3D MPJPE (mm): 21.0 -> 19.5Improved
replace max-heatmap-score weights with learned weightsScoreFuse · Human3.6M3D MPJPE (mm): 20.1 -> 19.5Improved
add geometry embedding to appearance embedding (ablation)AdaFuse · Human3.6M3D MPJPE (mm): 20.3 -> 19.5Improved
add appearance embedding to geometry embedding (ablation)AdaFuse · Human3.6M3D MPJPE (mm): 19.9 -> 19.5Improved
use multiview fusion instead of RANSAC outlier removalRANSAC · Human3.6M3D MPJPE (mm): 21.8 -> 19.5Improved
add AdaFuse fusionNoFuse · Occlusion-Person (occluded joints)2D PCKh@0.5 avg: 30.9 -> 95.5Improved
add AdaFuse fusionNoFuse · Occlusion-Person3D MPJPE (mm): 48.1 -> 12.6Improved
add AdaFuse fusionNoFuse · Occlusion-Person (joints occluded in 4 of 8 views)3D MPJPE (mm): 82.6 -> 21.7Improved
add AdaFuse fusion to joints visible in all viewsNoFuse · Occlusion-Person (joints visible in all views)3D MPJPE (mm): 13.0 -> 10.8Improved
add AdaFuse fusionNoFuse · Total Capture3D MPJPE (mm) mean: 29.4 -> 19.2Improved
add AdaFuse fusion to hip and head jointsNoFuse · Human3.6M3D MPJPE (mm): 17.8 -> 18.3 (Hip)Hurt

Later papers that compared with this method

2 later accepted papers report AdaFuse 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