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 is a core task in 3D computer vision. Recent methodsinvestigate the task of monocular depth trained with various depth sensormodalities. Every sensor has its advantages and drawbacks caused by the natureof estimates. In the literature, mostly mean average error of the depth isinvestigated and sensor capabilities are typically not discussed. Especiallyindoor environments, however, pose challenges for some devices. Texturelessregions pose challenges for structure from motion, reflective materials areproblematic for active sensing, and distances for translucent material areintricate to measure with existing sensors. This paper proposes HAMMER, adataset comprising depth estimates from multiple commonly used sensors forindoor depth estimation, namely ToF, stereo, structured light together withmonocular RGB+P data. We construct highly reliable ground truth depth maps withthe help of 3D scanners and aligned renderings. A popular depth estimators istrained on this data and typical depth senosors. The estimates are extensivelyanalyze on different scene structures. We notice generalization issues arisingfrom various sensor technologies in household environments with challenging buteveryday scene content. HAMMER, which we make publicly available, provides areliable base to pave the way to targeted depth improvements and sensor fusionapproaches.

Is my Depth Ground-Truth Good Enough? HAMMER -- Highly Accurate Multi-Modal Dataset for DEnse 3D Scene Regression