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

Hand pose estimation from a monocular RGB image is an important butchallenging task. The main factor affecting its performance is the lack of asufficiently large training dataset with accurate hand-keypoint annotations. Inthis work, we circumvent this problem by proposing an effective method forgenerating realistic hand poses and show that state-of-the-art algorithms forhand pose estimation can be greatly improved by utilizing the generated handposes as training data. Specifically, we first adopt an augmented reality (AR)simulator to synthesize hand poses with accurate hand-keypoint labels. Althoughthe synthetic hand poses come with precise joint labels, eliminating the needof manual annotations, they look unnatural and are not the ideal training data.To produce more realistic hand poses, we propose to blend a synthetic hand posewith a real background, such as arms and sleeves. To this end, we developtonality-alignment generative adversarial networks (TAGANs), which align thetonality and color distributions between synthetic hand poses and realbackgrounds, and can generate high quality hand poses. We evaluate TAGAN onthree benchmarks, including the RHP, STB, and CMU-PS hand pose datasets. Withthe aid of the synthesized poses, our method performs favorably against thestate-of-the-arts in both 2D and 3D hand pose estimations.

Generating Realistic Training Images Based on Tonality-Alignment Generative Adversarial Networks for Hand Pose Estimation