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

Estimating scene geometry from data obtained with cost-effective sensors iskey for robots and self-driving cars. In this paper, we study the problem ofpredicting dense depth from a single RGB image (monodepth) with optional sparsemeasurements from low-cost active depth sensors. We introduce Sparse AuxiliaryNetworks (SANs), a new module enabling monodepth networks to perform both thetasks of depth prediction and completion, depending on whether only RGB imagesor also sparse point clouds are available at inference time. First, we decouplethe image and depth map encoding stages using sparse convolutions to processonly the valid depth map pixels. Second, we inject this information, whenavailable, into the skip connections of the depth prediction network,augmenting its features. Through extensive experimental analysis on one indoor(NYUv2) and two outdoor (KITTI and DDAD) benchmarks, we demonstrate that ourproposed SAN architecture is able to simultaneously learn both tasks, whileachieving a new state of the art in depth prediction by a significant margin.

Sparse Auxiliary Networks for Unified Monocular Depth Prediction and Completion