AI Paper Atlas

Research map / 3D vision / Human pose estimation

Generalizable Human Pose Triangulation

Kristijan Bartol, David Bojanić, Tomislav Petković, Tomislav Pribanić

CVPR 2022 · 3D vision › Human pose estimation · approach: Multi-person pose estimation · 39 citations (OpenAlex)

Check 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
Use stochastic generalizable triangulation instead of Iskakov et al.'s volumetric approachHuman3.6M after training on CMU3 · CMU Panoptic Studio to Human3.6MMPJPE (mm): 34.0\,mm -> 31.0\,mm; 8.8%Improved
Use stochastic generalizable triangulation instead of RANSACCMU Panoptic Studio novel camera views · CMU Panoptic StudioMPJPE (mm): 39.5 -> 25.4Improved
Use stochastic generalizable triangulation instead of VoxelPoseCMU Panoptic Studio novel camera views · CMU Panoptic StudioMPJPE (mm): 25.5 -> 25.4Improved
Use stochastic generalizable triangulation instead of Epipolar transformersHuman3.6M, Protocol 1, abs. positions · Human3.6MMPJPE (mm): 26.9 -> 29.1Hurt
Use weighted hypothesis averaging rather than an unweighted average (ablation)Generalizable Human Pose Triangulation · Human3.6MMPJPE (mm): 31.2 -> 29.1Improved
Use weighted hypothesis averaging rather than selecting the most probable hypothesis (ablation)Generalizable Human Pose Triangulation · Human3.6MMPJPE (mm): 41.3 -> 29.1Improved
Use weighted hypothesis averaging rather than stochastic hypothesis selection (ablation)Generalizable Human Pose Triangulation · Human3.6MMPJPE (mm): 41.3 -> 29.1Improved
Use weighted hypothesis averaging rather than random hypothesis selection (ablation)Generalizable Human Pose Triangulation · CMU Panoptic StudioMPJPE (mm): 26.1 -> 24.9Improved
Use weighted hypothesis averaging rather than selecting the most probable hypothesis (ablation)Generalizable Human Pose Triangulation · CMU Panoptic StudioMPJPE (mm): 25.0 -> 24.9No clear effect
Estimate relative camera rotation while keeping translation known (ablation)Generalizable Human Pose Triangulation · Human3.6M, base camera arrangementMPJPE (mm): 29.1\,mm -> 29.4\,mmHurt
Estimate relative camera translation while keeping rotation known (ablation)Generalizable Human Pose Triangulation · Human3.6M, base camera arrangementMPJPE (mm): 29.1\,mm -> 36.7\,mmHurt
Estimate both relative camera rotation and translation (ablation)Generalizable Human Pose Triangulation · CMU3 to Human3.6MMPJPE (mm): 31.0\,mm -> 44.5\,mmHurt

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