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

Depth estimation from monocular images is pivotal for real-world visualperception systems. While current learning-based depth estimation models trainand test on meticulously curated data, they often overlook out-of-distribution(OoD) situations. Yet, in practical settings -- especially safety-critical oneslike autonomous driving -- common corruptions can arise. Addressing thisoversight, we introduce a comprehensive robustness test suite, RoboDepth,encompassing 18 corruptions spanning three categories: i) weather and lightingconditions; ii) sensor failures and movement; and iii) data processinganomalies. We subsequently benchmark 42 depth estimation models across indoorand outdoor scenes to assess their resilience to these corruptions. Ourfindings underscore that, in the absence of a dedicated robustness evaluationframework, many leading depth estimation models may be susceptible to typicalcorruptions. We delve into design considerations for crafting more robust depthestimation models, touching upon pre-training, augmentation, modality, modelcapacity, and learning paradigms. We anticipate our benchmark will establish afoundational platform for advancing robust OoD depth estimation.

RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptions