LocalBins: Improving Depth Estimation by Learning Local Distributions

Ibraheem Alhashim, Peter Wonka

Research output: Chapter in Book/Report/Conference proceedingConference contribution

11 Scopus citations


We propose a novel architecture for depth estimation from a single image. The architecture itself is based on the popular encoder-decoder architecture that is frequently used as a starting point for all dense regression tasks. We build on AdaBins which estimates a global distribution of depth values for the input image and evolve the architecture in two ways. First, instead of predicting global depth distributions, we predict depth distributions of local neighborhoods at every pixel. Second, instead of predicting depth distributions only towards the end of the decoder, we involve all layers of the decoder. We call this new architecture LocalBins. Our results demonstrate a clear improvement over the state-of-the-art in all metrics on the NYU-Depth V2 dataset. Code and pretrained models will be made publicly available.
Original languageEnglish (US)
Title of host publicationLecture Notes in Computer Science
PublisherSpringer Nature Switzerland
Number of pages17
ISBN (Print)9783031197680
StatePublished - Oct 23 2022

Bibliographical note

KAUST Repository Item: Exported on 2022-10-29
Acknowledged KAUST grant number(s): OSR-CRG2018-3730
Acknowledgements: This work was supported by the KAUST Office of Sponsored Research (OSR) under Award No. OSR-CRG2018-3730.

ASJC Scopus subject areas

  • Theoretical Computer Science
  • General Computer Science


Dive into the research topics of 'LocalBins: Improving Depth Estimation by Learning Local Distributions'. Together they form a unique fingerprint.

Cite this