AI Paper Atlas

Research map / 3D vision / Human pose estimation

MonoCap: Monocular Human Motion Capture using a CNN Coupled with a Geometric Prior

Xiaowei Zhou, Menglong Zhu, Georgios Pavlakos, Spyridon Leonardos, Konstantinos G. Derpanis, Kostas Daniilidis

TPAMI 2018 · 3D vision › Human pose estimation · approach: Human shape and pose regression · 228 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 temporal smoothness (ablation)MonoCap fine-tuned+specific · Human3.6Mper joint error (mm): 79.6 -> 77.8Improved
add temporal smoothness (ablation)MonoCap perspective, generic detector · Human3.6Mper joint error (mm): 106.0 -> 102.2Improved
add EM marginalization of 2D uncertainty (ablation)MonoCap perspective, fine-tuned · Human3.6Mper joint error (mm): 81.4 -> 79.6Improved
use EM instead of MAP estimation (ablation)MonoCap fine-tuned · Human3.6Mper joint error (mm): 79.3 -> 77.8Improved
use perspective instead of orthographic camera (ablation)MonoCap fine-tuned · Human3.6Mper joint error (mm): 92.5 -> 77.8Improved
use perspective instead of orthographic cameraMonoCap given 2D joints · Human3.6Mmean per joint error (mm): 88.7 -> 74.2Improved
fine-tune 2D detector on Human3.6MMonoCap nonspecific dictionary · Human3.6Mmean per joint error (mm): 107.8 -> 82.7Improved
use action-specific pose dictionaryMonoCap fine-tuned detector · Human3.6Mmean per joint error (mm): 82.7 -> 77.8Improved
use action-specific pose dictionaryMonoCap generic detector · Human3.6Mmean per joint error (mm): 107.8 -> 102.2Improved
enlarge dictionary from 32 to 128 atoms (ablation)MonoCap · Human3.6M Directions S9reconstruction error (mm): 48.1 -> 44.4Improved
use perspective model with 2D joints given (reconstruction)MonoCap · Human3.6M Protocol Ireconstruction error (mm): 51.1 -> 50.5No clear effect

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