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

Nighttime stereo depth estimation is still challenging, as assumptionsassociated with daytime lighting conditions do not hold any longer. Nighttimeis not only about low-light and dense noise, but also about glow/glare, flares,non-uniform distribution of light, etc. One of the possible solutions is totrain a network on night stereo images in a fully supervised manner. However,to obtain proper disparity ground-truths that are dense, independent fromglare/glow, and have sufficiently far depth ranges is extremely intractable. Toaddress the problem, we introduce a network joining day/night translation andstereo. In training the network, our method does not require ground-truthdisparities of the night images, or paired day/night images. We utilize atranslation network that can render realistic night stereo images from daystereo images. We then train a stereo network on the rendered night stereoimages using the available disparity supervision from the corresponding daystereo images, and simultaneously also train the day/night translation network.We handle the fake depth problem, which occurs due to the unsupervised/unpairedtranslation, for light effects (e.g., glow/glare) and uninformative regions(e.g., low-light and saturated regions), by adding structure-preservation andweighted-smoothness constraints. Our experiments show that our methodoutperforms the baseline methods on night images.

Nighttime Stereo Depth Estimation using Joint Translation-Stereo Learning: Light Effects and Uninformative Regions