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

There have been numerous recently proposed methods for monocular depthprediction (MDP) coupled with the equally rapid evolution of benchmarkingtools. However, we argue that MDP is currently witnessing benchmarkover-fitting and relying on metrics that are only partially helpful to gaugethe usefulness of the predictions for 3D applications. This limits the designand development of novel methods that are truly aware of - and improvingtowards estimating - the 3D structure of the scene rather than optimizing2D-based distances. In this work, we aim to bring structural awareness to MDP,an inherently 3D task, by exhibiting the limits of evaluation metrics towardsassessing the quality of the 3D geometry. We propose a set of metrics wellsuited to evaluate the 3D geometry of MDP approaches and a novel indoorbenchmark, RIO-D3D, crucial for the proposed evaluation methodology. Ourbenchmark is based on a real-world dataset featuring high-quality rendereddepth maps obtained from RGB-D reconstructions. We further demonstrate this tohelp benchmark the closely-tied task of 3D scene completion.

From 2D to 3D: Re-thinking Benchmarking of Monocular Depth Prediction