AI Paper Atlas

Research map / 3D vision / Human pose estimation

Learnable Triangulation of Human Pose

Karim Iskakov, Egor Burkov, Victor Lempitsky, Yury Malkov

ICCV 2019 · 3D vision › Human pose estimation · approach: Monocular 2D-to-3D pose lifting · 473 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 learned camera-joint confidences to algebraic triangulation (ablation)algebraic triangulation · Human3.6M (Protocol 1, relative to pelvis, average)MPJPE (mm): 26.9 -> 22.6Improved
add learned confidences to algebraic triangulation (ablation)algebraic triangulation · CMU Panoptic validation (4 cameras)MPJPE (mm): 33.4 -> 21.3Improved
add learned confidences to algebraic triangulation (ablation)algebraic triangulation · Human3.6M (absolute positions, filtered validation, average)MPJPE (mm): 24.5 -> 19.2Improved
use volumetric triangulation instead of algebraictriangulation · Human3.6M (Protocol 1, relative to pelvis, average)MPJPE (mm): 22.6 -> 20.8Improved
use volumetric triangulation instead of algebraictriangulation · CMU Panoptic validation (4 cameras)MPJPE (mm): 21.3 -> 13.7Improved
use volumetric triangulation instead of algebraictriangulation · Human3.6M (absolute positions, filtered validation, average)MPJPE (mm): 19.2 -> 17.7Improved
use algebraic triangulation with confidences instead of RANSACtriangulation · Human3.6M (Protocol 1, relative to pelvis, average)MPJPE (mm): 27.4 -> 22.6Improved
use softmax aggregation instead of sum aggregation of view volumes (ablation)volumetric triangulation · Human3.6M (Protocol 1, relative to pelvis, average)MPJPE (mm): 21.3 -> 20.8Improved
use softmax aggregation instead of confidence aggregation (ablation)volumetric triangulation · CMU Panoptic validation (4 cameras)MPJPE (mm): 14.0 -> 13.7No clear effect
add heatmap regularizer (beta 0.01) to volumetric L1 loss (ablation)volumetric triangulation · Human3.6M (Protocol 1, relative to pelvis, average)MPJPE (mm)No clear effect
use algebraic soft-MSE loss instead of L1 in volumetric triangulation (ablation)volumetric triangulation · Human3.6M (Protocol 1, relative to pelvis, average)MPJPE (mm)Hurt
train on CMU and test on Human3.6M instead of training on Human3.6Mvolumetric triangulation · CMU-trained model on Human3.6M (elbows, wrists, knees)MPJPE (mm): 16-18 -> 34Hurt

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