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 explore learning pixelwise correspondences between images of deformableobjects in different configurations. Traditional correspondence matchingapproaches such as SIFT, SURF, and ORB can fail to provide sufficientcontextual information for fine-grained manipulation. We propose Multi-ModalGaussian Shape Descriptor (MMGSD), a new visual representation of deformableobjects which extends ideas from dense object descriptors to predict allsymmetric correspondences between different object configurations. MMGSD islearned in a self-supervised manner from synthetic data and producescorrespondence heatmaps with measurable uncertainty. In simulation, experimentssuggest that MMGSD can achieve an RMSE of 32.4 and 31.3 for square cloth andbraided synthetic nylon rope respectively. The results demonstrate an averageof 47.7% improvement over a provided baseline based on contrastive learning,symmetric pixel-wise contrastive loss (SPCL), as opposed to MMGSD whichenforces distributional continuity.

MMGSD: Multi-Modal Gaussian Shape Descriptors for Correspondence Matching in 1D and 2D Deformable Objects