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 an approach to learn dense, continuous 2D-3D correspondencedistributions over the surface of objects from data with no prior knowledge ofvisual ambiguities like symmetry. We also present a new method for 6D poseestimation of rigid objects using the learnt distributions to sample, score andrefine pose hypotheses. The correspondence distributions are learnt with acontrastive loss, represented in object-specific latent spaces by anencoder-decoder query model and a small fully connected key model. Our methodis unsupervised with respect to visual ambiguities, yet we show that the query-and key models learn to represent accurate multi-modal surface distributions.Our pose estimation method improves the state-of-the-art significantly on thecomprehensive BOP Challenge, trained purely on synthetic data, even comparedwith methods trained on real data. The project site is athttps://surfemb.github.io/ .

SurfEmb: Dense and Continuous Correspondence Distributions for Object Pose Estimation with Learnt Surface Embeddings