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/

Zendy Plus

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

Zendy Tools

Zendy Open

It is difficult to precisely annotate object instances and their semantics in3D space, and as such, synthetic data are extensively used for these tasks,e.g., category-level 6D object pose and size estimation. However, the easyannotations in synthetic domains bring the downside effect of synthetic-to-real(Sim2Real) domain gap. In this work, we aim to address this issue in the tasksetting of Sim2Real, unsupervised domain adaptation for category-level 6Dobject pose and size estimation. We propose a method that is built upon a novelDeep Prior Deformation Network, shortened as DPDN. DPDN learns to deformfeatures of categorical shape priors to match those of object observations, andis thus able to establish deep correspondence in the feature space for directregression of object poses and sizes. To reduce the Sim2Real domain gap, weformulate a novel self-supervised objective upon DPDN via consistency learning;more specifically, we apply two rigid transformations to each objectobservation in parallel, and feed them into DPDN respectively to yield dualsets of predictions; on top of the parallel learning, an inter-consistency termis employed to keep cross consistency between dual predictions for improvingthe sensitivity of DPDN to pose changes, while individual intra-consistencyones are used to enforce self-adaptation within each learning itself. We trainDPDN on both training sets of the synthetic CAMERA25 and real-world REAL275datasets; our results outperform the existing methods on REAL275 test set underboth the unsupervised and supervised settings. Ablation studies also verify theefficacy of our designs. Our code is released publicly athttps://github.com/JiehongLin/Self-DPDN.

Category-Level 6D Object Pose and Size Estimation using Self-Supervised Deep Prior Deformation Networks