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/

Zendy Plus

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

Zendy Tools

Zendy Open

We present a joint 3D pose and focal length estimation approach for objectcategories in the wild. In contrast to previous methods that predict 3D posesindependently of the focal length or assume a constant focal length, weexplicitly estimate and integrate the focal length into the 3D pose estimation.For this purpose, we combine deep learning techniques and geometric algorithmsin a two-stage approach: First, we estimate an initial focal length andestablish 2D-3D correspondences from a single RGB image using a deep network.Second, we recover 3D poses and refine the focal length by minimizing thereprojection error of the predicted correspondences. In this way, we exploitthe geometric prior given by the focal length for 3D pose estimation. Thisresults in two advantages: First, we achieve significantly improved 3Dtranslation and 3D pose accuracy compared to existing methods. Second, ourapproach finds a geometric consensus between the individual projectionparameters, which is required for precise 2D-3D alignment. We evaluate ourproposed approach on three challenging real-world datasets (Pix3D, Comp, andStanford) with different object categories and significantly outperform thestate-of-the-art by up to 20% absolute in multiple different metrics.

GP2C: Geometric Projection Parameter Consensus for Joint 3D Pose and Focal Length Estimation in the Wild