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

An emerging problem in computer vision is the reconstruction of 3D shape andpose of an object from a single image. Hitherto, the problem has been addressedthrough the application of canonical deep learning methods to regress from theimage directly to the 3D shape and pose labels. These approaches, however, areproblematic from two perspectives. First, they are minimizing the error between3D shapes and pose labels - with little thought about the nature of this labelerror when reprojecting the shape back onto the image. Second, they rely on theonerous and ill-posed task of hand labeling natural images with respect to 3Dshape and pose. In this paper we define the new task of pose-aware shapereconstruction from a single image, and we advocate that cheaper 2D annotationsof objects silhouettes in natural images can be utilized. We designarchitectures of pose-aware shape reconstruction which re-project the predictedshape back on to the image using the predicted pose. Our evaluation on severalobject categories demonstrates the superiority of our method for predictingpose-aware 3D shapes from natural images.

Rethinking Reprojection: Closing the Loop for Pose-aware ShapeReconstruction from a Single Image