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 present a deep learning method for end-to-end monocular 3D objectdetection and metric shape retrieval. We propose a novel loss formulation bylifting 2D detection, orientation, and scale estimation into 3D space. Insteadof optimizing these quantities separately, the 3D instantiation allows toproperly measure the metric misalignment of boxes. We experimentally show thatour 10D lifting of sparse 2D Regions of Interests (RoIs) achieves great resultsboth for 6D pose and recovery of the textured metric geometry of instances.This further enables 3D synthetic data augmentation via inpainting recoveredmeshes directly onto the 2D scenes. We evaluate on KITTI3D against other strongmonocular methods and demonstrate that our approach doubles the AP on the 3Dpose metrics on the official test set, defining the new state of the art.

ROI-10D: Monocular Lifting of 2D Detection to 6D Pose and Metric Shape