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 learning techniques have enabled rapid progress in monocular depthestimation, but their quality is limited by the ill-posed nature of the problemand the scarcity of high quality datasets. We estimate depth from a singlecamera by leveraging the dual-pixel auto-focus hardware that is increasinglycommon on modern camera sensors. Classic stereo algorithms and priorlearning-based depth estimation techniques under-perform when applied on thisdual-pixel data, the former due to too-strong assumptions about RGB imagematching, and the latter due to not leveraging the understanding of optics ofdual-pixel image formation. To allow learning based methods to work well ondual-pixel imagery, we identify an inherent ambiguity in the depth estimatedfrom dual-pixel cues, and develop an approach to estimate depth up to thisambiguity. Using our approach, existing monocular depth estimation techniquescan be effectively applied to dual-pixel data, and much smaller models can beconstructed that still infer high quality depth. To demonstrate this, wecapture a large dataset of in-the-wild 5-viewpoint RGB images paired withcorresponding dual-pixel data, and show how view supervision with this data canbe used to learn depth up to the unknown ambiguities. On our new task, ourmodel is 30% more accurate than any prior work on learning-based monocular orstereoscopic depth estimation.

Learning Single Camera Depth Estimation using Dual-Pixels