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

Estimating 3D hand meshes from single RGB images is challenging, due tointrinsic 2D-3D mapping ambiguities and limited training data. We adopt acompact parametric 3D hand model that represents deformable and articulatedhand meshes. To achieve the model fitting to RGB images, we investigate andcontribute in three ways: 1) Neural rendering: inspired by recent work on humanbody, our hand mesh estimator (HME) is implemented by a neural network and adifferentiable renderer, supervised by 2D segmentation masks and 3D skeletons.HME demonstrates good performance for estimating diverse hand shapes andimproves pose estimation accuracies. 2) Iterative testing refinement: Ourfitting function is differentiable. We iteratively refine the initial estimateusing the gradients, in the spirit of iterative model fitting methods like ICP.The idea is supported by the latest research on human body. 3) Self-dataaugmentation: collecting sized RGB-mesh (or segmentation mask)-skeletontriplets for training is a big hurdle. Once the model is successfully fitted toinput RGB images, its meshes i.e. shapes and articulations, are realistic, andwe augment view-points on top of estimated dense hand poses. Experiments usingthree RGB-based benchmarks show that our framework offers beyondstate-of-the-art accuracy in 3D pose estimation, as well as recovers dense 3Dhand shapes. Each technical component above meaningfully improves the accuracyin the ablation study.

Pushing the Envelope for RGB-based Dense 3D Hand Pose Estimation via Neural Rendering