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

6-DoF object pose estimation from a monocular image is challenging, and apost-refinement procedure is generally needed for high-precision estimation. Inthis paper, we propose a framework based on a recurrent neural network (RNN)for object pose refinement, which is robust to erroneous initial poses andocclusions. During the recurrent iterations, object pose refinement isformulated as a non-linear least squares problem based on the estimatedcorrespondence field (between a rendered image and the observed image). Theproblem is then solved by a differentiable Levenberg-Marquardt (LM) algorithmenabling end-to-end training. The correspondence field estimation and poserefinement are conducted alternatively in each iteration to recover the objectposes. Furthermore, to improve the robustness to occlusion, we introduce aconsistency-check mechanism based on the learned descriptors of the 3D modeland observed 2D images, which downweights the unreliable correspondences duringpose optimization. Extensive experiments on LINEMOD, Occlusion-LINEMOD, andYCB-Video datasets validate the effectiveness of our method and demonstratestate-of-the-art performance.

RNNPose: Recurrent 6-DoF Object Pose Refinement with Robust Correspondence Field Estimation and Pose Optimization