AI Paper Atlas

Research map / 3D vision / Human pose estimation

Cross View Fusion for 3D Human Pose Estimation

Haibo Qiu, Chunyu Wang, Jingdong Wang, Naiyan Wang, Wenjun Zeng

ICCV 2019 · 3D vision › Human pose estimation · approach: Multi-person pose estimation · 253 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 cross-view feature fusion (vs Single), trained on H36M+MPII, triangulation (ablation)Single baseline · Human3.6M testMPJPE (mm) average: 36.28 -> 27.90Improved
add cross-view feature fusion, trained on H36M only, triangulation (ablation)Single baseline · Human3.6M testMPJPE (mm) average: 94.54 -> 38.29Improved
add cross-view feature fusion, trained on H36M only, RPSM (ablation)Single baseline · Human3.6M testMPJPE (mm) average: 47.82 -> 31.17Improved
add the fusion network instead of sum or max over epipolar lines (ablation)Sum/Max baselines · Human3.6M 2D wristjoint detection rate wrist (%): 91.57 -> 95.01Improved
add recursive refinement (RPSM) instead of triangulation, H36M only (ablation)Single · Human3.6M testMPJPE (mm) average: 94.54 -> 47.82Improved
add recursive refinement (RPSM) instead of triangulation, H36M+MPII (ablation)Fusion · Human3.6M testMPJPE (mm) average: 27.90 -> 26.21Improved
add recursive refinement (RPSM) instead of triangulation on the Sitting action (ablation)Fusion +MPII · Human3.6M testMPJPE (mm) Sitting: 40.47 -> 32.12Improved
run RPSM refinement iterations t=10 instead of PSM (t=0) (ablation)Single-H36M · Human3.6M test (RPSM iterations)MPJPE (mm): 95.23 -> 47.82Improved
run RPSM refinement iterations t=10 instead of PSM (t=0) (ablation)Fusion-+MPII · Human3.6M test (RPSM iterations)MPJPE (mm): 77.28 -> 26.21Improved
increase RPSM iterations from t=5 to t=10 (ablation)Fusion-+MPII · Human3.6M test (RPSM iterations)MPJPE (mm): 26.26 -> 26.21No clear effect
add cross-view fusion on Total Capture (ablation)Single-RPSM · Total CaptureMPJPE (mm) mean: 41 -> 29Improved
add training data MPII to H36M for 2D estimation, no fusion, triangulation (ablation)Single · Human3.6M testMPJPE (mm) average: 94.54 -> 36.28Improved

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