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

Indoor monocular depth estimation has attracted increasing research interest.Most previous works have been focusing on methodology, primarily experimentingwith NYU-Depth-V2 (NYUv2) Dataset, and only concentrated on the overallperformance over the test set. However, little is known regarding robustnessand generalization when it comes to applying monocular depth estimation methodsto real-world scenarios where highly varying and diverse functional\textit{space types} are present such as library or kitchen. A study forperformance breakdown into space types is essential to realize a pretrainedmodel's performance variance. To facilitate our investigation for robustnessand address limitations of previous works, we collect InSpaceType, ahigh-quality and high-resolution RGBD dataset for general indoor environments.We benchmark 11 recent methods on InSpaceType and find they severely sufferfrom performance imbalance concerning space types, which reveals theirunderlying bias. We extend our analysis to 4 other datasets, 3 mitigationapproaches, and the ability to generalize to unseen space types. Our work marksthe first in-depth investigation of performance imbalance across space typesfor indoor monocular depth estimation, drawing attention to potential safetyconcerns for model deployment without considering space types, and furthershedding light on potential ways to improve robustness. See\url{https://depthcomputation.github.io/DepthPublic} for data.

InSpaceType: Reconsider Space Type in Indoor Monocular Depth Estimation