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

Depth estimation is an important step in many computer vision problems suchas 3D reconstruction, novel view synthesis, and computational photography. Mostexisting work focuses on depth estimation from single frames. When applied tovideos, the result lacks temporal consistency, showing flickering and swimmingartifacts. In this paper we aim to estimate temporally consistent depth maps ofvideo streams in an online setting. This is a difficult problem as futureframes are not available and the method must choose between enforcingconsistency and correcting errors from previous estimations. The presence ofdynamic objects further complicates the problem. We propose to address thesechallenges by using a global point cloud that is dynamically updated eachframe, along with a learned fusion approach in image space. Our approachencourages consistency while simultaneously allowing updates to handle errorsand dynamic objects. Qualitative and quantitative results show that our methodachieves state-of-the-art quality for consistent video depth estimation.

Temporally Consistent Online Depth Estimation Using Point-Based Fusion