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

In this paper, a self-supervised model that simultaneously predicts asequence of future frames from video-input with a novel spatial-temporalattention (ST) network is proposed. The ST transformer network allowsconstraining both temporal consistency across future frames whilst constrainingconsistency across spatial objects in the image at different scales. This wasnot the case in prior works for depth prediction, which focused on predicting asingle frame as output. The proposed model leverages prior scene knowledge suchas object shape and texture similar to single-image depth inference methods,whilst also constraining the motion and geometry from a sequence of inputimages. Apart from the transformer architecture, one of the main contributionswith respect to prior works lies in the objective function that enforcesspatio-temporal consistency across a sequence of output frames rather than asingle output frame. As will be shown, this results in more accurate and robustdepth sequence forecasting. The model achieves highly accurate depthforecasting results that outperform existing baselines on the KITTI benchmark.Extensive ablation studies were performed to assess the effectiveness of theproposed techniques. One remarkable result of the proposed model is that it isimplicitly capable of forecasting the motion of objects in the scene, ratherthan requiring complex models involving multi-object detection, segmentationand tracking.

STDepthFormer: Predicting Spatio-temporal Depth from Video with a Self-supervised Transformer Model