AI Paper Atlas

Research map / 3D vision / Human pose estimation

Learning to Fuse 2D and 3D Image Cues for Monocular Body Pose Estimation

Bugra Tekin, Pablo Marquez-Neila, Mathieu Salzmann, Pascal Fua

ICCV 2017 · 3D vision › Human pose estimation · approach: Monocular 2D-to-3D pose lifting · 247 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 confidence map stream to image stream (early fusion) (ablation)Image-Only regressor · Human3.6m3D joint position error (mm): 124.13 -> 76.41Improved
add image stream to confidence map stream (late fusion) (ablation)CM-Only regressor · Human3.6m3D joint position error (mm): 79.28 -> 74.12Improved
learn the fusion layer instead of late fusion (ablation)two-stream network · Human3.6m3D joint position error (mm): 74.12 -> 69.73Improved
learn the fusion layer instead of early fusion (ablation)two-stream network · Human3.6m3D joint position error (mm): 76.41 -> 69.73Improved
add sharp-fusion regularization term (ablation)trainable fusion · Human3.6m Eating3D joint position error (mm): 68.30 -> 60.17Improved
add sharp-fusion regularization term (pruning) (ablation)trainable fusion · Human3.6m Eatingruntime (sec/frame): 0.013 -> 0.006Improved
pretrain on synthetic 3D pose data before fine-tuning (ablation)trainable fusion · KTH Multiview Football IIPCP all parts (%): 83.2 -> 95.2Improved
replace single-stage fully-convolutional 2D detector with stacked hourglass (ablation)confidence map stream · Human3.6m3D pose accuracyImproved
use fusion of 2D confidence maps and image cues instead of prior single-image methodstrainable fusion · Human3.6m (all actions)3D joint position error (mm): 107.26 -> 69.73Improved
use trainable fusion instead of prior methods on HumanEva-Itrainable fusion · HumanEva-I Walking3D joint position error (mm): 36.6 -> 24.41Improved

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