English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

To improve the generalization of 3D human pose estimators, many existing deeplearning based models focus on adding different augmentations to trainingposes. However, data augmentation techniques are limited to the "seen" posecombinations and hard to infer poses with rare "unseen" joint positions. Toaddress this problem, we present CameraPose, a weakly-supervised framework for3D human pose estimation from a single image, which can not only be applied on2D-3D pose pairs but also on 2D alone annotations. By adding a camera parameterbranch, any in-the-wild 2D annotations can be fed into our pipeline to boostthe training diversity and the 3D poses can be implicitly learned byreprojecting back to 2D. Moreover, CameraPose introduces a refinement networkmodule with confidence-guided loss to further improve the quality of noisy 2Dkeypoints extracted by 2D pose estimators. Experimental results demonstratethat the CameraPose brings in clear improvements on cross-scenario datasets.Notably, it outperforms the baseline method by 3mm on the most challengingdataset 3DPW. In addition, by combining our proposed refinement network modulewith existing 3D pose estimators, their performance can be improved incross-scenario evaluation.

CameraPose: Weakly-Supervised Monocular 3D Human Pose Estimation by Leveraging In-the-wild 2D Annotations