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

This paper proposes a new method to infer keypoints from arbitrary objectcategories in practical scenarios where point cloud data (PCD) are noisy,down-sampled and arbitrarily rotated. Our proposed model adheres to thefollowing principles: i) keypoints inference is fully unsupervised (noannotation given), ii) keypoints position error should be low and resilient toPCD perturbations (robustness), iii) keypoints should not change their indexesfor the intra-class objects (semantic coherence), iv) keypoints should be closeto or proximal to PCD surface (compactness). We achieve these desiderata byproposing a new self-supervised training strategy for keypoints estimation thatdoes not assume any a priori knowledge of the object class, and a modelarchitecture with coupled auxiliary losses that promotes the desired keypointsproperties. We compare the keypoints estimated by the proposed approach withthose of the state-of-the-art unsupervised approaches. The experiments showthat our approach outperforms by estimating keypoints with improved coverage(+9.41%) while being semantically consistent (+4.66%) that best characterizesthe object's 3D shape for downstream tasks. Code and data are available at:https://github.com/IITPAVIS/SC3K

SC3K: Self-supervised and Coherent 3D Keypoints Estimation from Rotated, Noisy, and Decimated Point Cloud Data