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

We study the problem of estimating 3D shape and pose of an object in terms ofkeypoints, from a single 2D image.  The shape and pose are learned directly from images collected by categoriesand their partial 2D keypoint annotations.. In this work, we first propose anend-to-end training framework for intermediate 2D keypoints extraction andfinal 3D shape and pose estimation. The proposed framework is then trainedusing only the weak supervision of the intermediate 2D keypoints. Additionally,we devise a semi-supervised training framework that benefits from both labeledand unlabeled data. To leverage the unlabeled data, we introduce and exploitthe \emph{piece-wise planar hull} prior of the canonical object shape. Theseplanar hulls are defined manually once per object category, with the help ofthe keypoints. On the one hand, the proposed method learns to segment theseplanar hulls from the labeled data. On the other hand, it simultaneouslyenforces the consistency between predicted keypoints and the segmented hulls onthe unlabeled data. The enforced consistency allows us to efficiently use theunlabeled data for the task at hand. The proposed method achieves comparableresults with fully supervised state-of-the-art methods by using only half ofthe annotations. Our source code will be made publicly available.

Piecewise Planar Hulls for Semi-Supervised Learning of 3D Shape and Pose from 2D Images