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

Estimating a dense and accurate depth map is the key requirement forautonomous driving and robotics. Recent advances in deep learning have alloweddepth estimation in full resolution from a single image. Despite thisimpressive result, many deep-learning-based monocular depth estimation (MDE)algorithms have failed to keep their accuracy yielding a meter-level estimationerror. In many robotics applications, accurate but sparse measurements arereadily available from Light Detection and Ranging (LiDAR). Although they arehighly accurate, the sparsity limits full resolution depth map reconstruction.Targeting the problem of dense and accurate depth map recovery, this paperintroduces the fusion of these two modalities as a depth completion (DC)problem by dividing the role of depth inference and depth regression. Utilizingthe state-of-the-art MDE and our Gaussian process (GP) based depth-regressionmethod, we propose a general solution that can flexibly work with various MDEmodules by enhancing its depth with sparse range measurements. To overcome themajor limitation of GP, we adopt Kernel Interpolation for Scalable Structured(KISS)-GP and mitigate the computational complexity from O(N^3) to O(N). Ourexperiments demonstrate that the accuracy and robustness of our methodoutperform state-of-the-art unsupervised methods for sparse and biasedmeasurements.

Balanced Depth Completion between Dense Depth Inference and Sparse Range Measurements via KISS-GP