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

We tackle the fundamentally ill-posed problem of 3D human localization frommonocular RGB images. Driven by the limitation of neural networks outputtingpoint estimates, we address the ambiguity in the task by predicting confidenceintervals through a loss function based on the Laplace distribution. Ourarchitecture is a light-weight feed-forward neural network that predicts 3Dlocations and corresponding confidence intervals given 2D human poses. Thedesign is particularly well suited for small training data, cross-datasetgeneralization, and real-time applications. Our experiments show that we (i)outperform state-of-the-art results on KITTI and nuScenes datasets, (ii) evenoutperform a stereo-based method for far-away pedestrians, and (iii) estimatemeaningful confidence intervals. We further share insights on our model ofuncertainty in cases of limited observations and out-of-distribution samples.

MonoLoco: Monocular 3D Pedestrian Localization and Uncertainty Estimation