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/

Zendy Plus

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

Zendy Tools

Zendy Open

We propose a learning-based multi-view stereo (MVS) method in scatteringmedia, such as fog or smoke, with a novel cost volume, called the dehazing costvolume. Images captured in scattering media are degraded due to lightscattering and attenuation caused by suspended particles. This degradationdepends on scene depth; thus, it is difficult for traditional MVS methods toevaluate photometric consistency because the depth is unknown beforethree-dimensional (3D) reconstruction. The dehazing cost volume can solve thischicken-and-egg problem of depth estimation and image restoration by computingthe scattering effect using swept planes in the cost volume. We also propose amethod of estimating scattering parameters, such as airlight, and a scatteringcoefficient, which are required for our dehazing cost volume. The output depthof a network with our dehazing cost volume can be regarded as a function ofthese parameters; thus, they are geometrically optimized with a sparse 3D pointcloud obtained at a structure-from-motion step. Experimental results onsynthesized hazy images indicate the effectiveness of our dehazing cost volumeagainst the ordinary cost volume regarding scattering media. We alsodemonstrated the applicability of our dehazing cost volume to real foggyscenes.

Dehazing Cost Volume for Deep Multi-view Stereo in Scattering Media with Airlight and Scattering Coefficient Estimation