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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Recently Transformers have provided state-of-the-art performance in sparsematching, crucial to realize high-performance 3D vision applications. Yet,these Transformers lack efficiency due to the quadratic computationalcomplexity of their attention mechanism. To solve this problem, we employ anefficient linear attention for the linear computational complexity. Then, wepropose a new attentional aggregation that achieves high accuracy byaggregating both the global and local information from sparse keypoints. Tofurther improve the efficiency, we propose the joint learning of featurematching and description. Our learning enables simpler and faster matching thanSinkhorn, often used in matching the learned descriptors from Transformers. Ourmethod achieves competitive performance with only 0.84M learnable parametersagainst the bigger SOTAs, SuperGlue (12M parameters) and SGMNet (30Mparameters), on three benchmarks, HPatch, ETH, and Aachen Day-Night.

Efficient Linear Attention for Fast and Accurate Keypoint Matching