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

Learning-based multi-view stereo (MVS) methods have made impressive progressand surpassed traditional methods in recent years. However, their accuracy andcompleteness are still struggling. In this paper, we propose a new method toenhance the performance of existing networks inspired by contrastive learningand feature matching. First, we propose a Contrast Matching Loss (CML), whichtreats the correct matching points in depth-dimension as positive sample andother points as negative samples, and computes the contrastive loss based onthe similarity of features. We further propose a Weighted Focal Loss (WFL) forbetter classification capability, which weakens the contribution oflow-confidence pixels in unimportant areas to the loss according to predictedconfidence. Extensive experiments performed on DTU, Tanks and Temples andBlendedMVS datasets show our method achieves state-of-the-art performance andsignificant improvement over baseline network.

Enhancing Multi-view Stereo with Contrastive Matching and Weighted Focal Loss