AI Paper Atlas

Research map / 3D vision / Human pose estimation

TexturePose: Supervising Human Mesh Estimation With Texture Consistency

Georgios Pavlakos, Nikos Kolotouros, Kostas Daniilidis

ICCV 2019 · 3D vision › Human pose estimation · approach: Human shape and pose regression · 114 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 texture consistency loss over short monocular clips (ablation)2D keypoints + GAN prior · Human3.6M Protocol 1reconstruction error (mm): 93.0 -> 80.2Improved
add texture consistency loss over short monocular clips (ablation)2D keypoints + GAN prior · Human3.6M Protocol 2reconstruction error (mm): 79.1 -> 76.2Improved
add unlabeled MPII video frames with texture consistency (ablation)H36M 3D supervised model · Human3.6M Protocol 1reconstruction error (mm): 64.8 -> 60.1Improved
add unlabeled MPII video frames with texture consistency (ablation)H36M 3D supervised model · Human3.6M Protocol 2reconstruction error (mm): 63.9 -> 58.6Improved
add MPII 2D keypoint annotationsH36M 3D supervised model · Human3.6M Protocol 1reconstruction error (mm): 64.8 -> 54.1Improved
add unlabeled MPII video frames with texture consistency on top of MPII 2D (ablation)H36M + MPII 2D · Human3.6M Protocol 1reconstruction error (mm): 54.1 -> 51.3Improved
add unlabeled MPII video frames with texture consistency on top of MPII 2D (ablation)H36M + MPII 2D · Human3.6M Protocol 2reconstruction error (mm): 51.6 -> 49.7Improved
add texture consistency (vs 3D ground truth for every image) (ablation)2D keypoints + GAN prior · Human3.6M Protocol 1reconstruction error (mm): 93.0 -> 80.2Improved
use TexturePose instead of HMRHMR · Human3.6M Protocol 2reconstruction error (mm): 56.8 -> 49.7Improved
use TexturePose instead of HMRHMR · LSP part segmentationaccuracy: 87.12 -> 89.00Improved
use TexturePose instead of HMRHMR · LSP foreground-background segmentationaccuracy: 91.67 -> 91.82Improved
use TexturePose instead of Rhodin et al. (second)Rhodin et al. · Human3.6M Protocol 1 multi-viewMPJPE (mm): 131.7 -> 110.7Improved

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