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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Recent studies have witnessed that self-supervised methods based on viewsynthesis obtain clear progress on multi-view stereo (MVS). However, existingmethods rely on the assumption that the corresponding points among differentviews share the same color, which may not always be true in practice. This maylead to unreliable self-supervised signal and harm the final reconstructionperformance. To address the issue, we propose a framework integrated with morereliable supervision guided by semantic co-segmentation and data-augmentation.Specially, we excavate mutual semantic from multi-view images to guide thesemantic consistency. And we devise effective data-augmentation mechanism whichensures the transformation robustness by treating the prediction of regularsamples as pseudo ground truth to regularize the prediction of augmentedsamples. Experimental results on DTU dataset show that our proposed methodsachieve the state-of-the-art performance among unsupervised methods, and evencompete on par with supervised methods. Furthermore, extensive experiments onTanks&Temples dataset demonstrate the effective generalization ability of theproposed method.

Self-supervised Multi-view Stereo via Effective Co-Segmentation and Data-Augmentation