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

The objective of this work is to estimate 3D human pose from a single RGBimage. Extracting image representations which incorporate both spatial relationof body parts and their relative depth plays an essential role in accurate3Dpose reconstruction. In this paper, for the first time, we show that cameraviewpoint in combination to 2D joint lo-cations significantly improves 3D poseaccuracy without the explicit use of perspective geometry mathematicalmodels.To this end, we train a deep Convolutional Neural Net-work (CNN) tolearn categorical camera viewpoint. To make the network robust against clothingand body shape of the subject in the image, we utilized 3D computer renderingto synthesize additional training images. We test our framework on the largest3D pose estimation bench-mark, Human3.6m, and achieve up to 20% error reductioncompared to the state-of-the-art approaches that do not use body partsegmentation.

Learning camera viewpoint using CNN to improve 3D body pose estimation