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

Deep neural networks have recently thrived on single image depth estimation.That being said, current developments on this topic highlight an apparentcompromise between accuracy and network size. This work proposes an accurateand lightweight framework for monocular depth estimation based on aself-attention mechanism stemming from salient point detection. Specifically,we utilize a sparse set of keypoints to train a FuSaNet model that consists oftwo major components: Fusion-Net and Saliency-Net. In addition, we introduce anormalized Hessian loss term invariant to scaling and shear along the depthdirection, which is shown to substantially improve the accuracy. The proposedmethod achieves state-of-the-art results on NYU-Depth-v2 and KITTI while using3.1-38.4 times smaller model in terms of the number of parameters than baselineapproaches. Experiments on the SUN-RGBD further demonstrate thegeneralizability of the proposed method.

Monocular Depth Estimation Primed by Salient Point Detection and Normalized Hessian Loss