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

Attention-based models such as transformers have shown outstandingperformance on dense prediction tasks, such as semantic segmentation, owing totheir capability of capturing long-range dependency in an image. However, thebenefit of transformers for monocular depth prediction has seldom been exploredso far. This paper benchmarks various transformer-based models for the depthestimation task on an indoor NYUV2 dataset and an outdoor KITTI dataset. Wepropose a novel attention-based architecture, Depthformer for monocular depthestimation that uses multi-head self-attention to produce the multiscalefeature maps, which are effectively combined by our proposed decoder network.We also propose a Transbins module that divides the depth range into bins whosecenter value is estimated adaptively per image. The final depth estimated is alinear combination of bin centers for each pixel. Transbins module takesadvantage of the global receptive field using the transformer module in theencoding stage. Experimental results on NYUV2 and KITTI depth estimationbenchmark demonstrate that our proposed method improves the state-of-the-art by3.3%, and 3.3% respectively in terms of Root Mean Squared Error (RMSE). Code isavailable at https://github.com/ashutosh1807/Depthformer.git.

Depthformer : Multiscale Vision Transformer For Monocular Depth Estimation With Local Global Information Fusion