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

Establishing dense correspondences between multiple images is a fundamentaltask in many applications. However, finding a reliable correspondence inmulti-modal or multi-spectral images still remains unsolved due to theirchallenging photometric and geometric variations. In this paper, we propose anovel dense descriptor, called dense adaptive self-correlation (DASC), toestimate multi-modal and multi-spectral dense correspondences. Based on anobservation that self-similarity existing within images is robust to imagingmodality variations, we define the descriptor with a series of an adaptiveself-correlation similarity measure between patches sampled by a randomizedreceptive field pooling, in which a sampling pattern is obtained using adiscriminative learning. The computational redundancy of dense descriptors isdramatically reduced by applying fast edge-aware filtering. Furthermore, inorder to address geometric variations including scale and rotation, we proposea geometry-invariant DASC (GI-DASC) descriptor that effectively leverages theDASC through a superpixel-based representation. For a quantitative evaluationof the GI-DASC, we build a novel multi-modal benchmark as varying photometricand geometric conditions. Experimental results demonstrate the outstandingperformance of the DASC and GI-DASC in many cases of multi-modal andmulti-spectral dense correspondences.

DASC: Robust Dense Descriptor for Multi-modal and Multi-spectral Correspondence Estimation