Back to articles
Articles
Volume: 32 | Article ID: art00020
Image
Sky Segmentation for Enhanced Depth Reconstruction and Bokeh Rendering with Efficient Architectures
  DOI :  10.2352/ISSN.2470-1173.2020.14.COIMG-378  Published OnlineJanuary 2020
Abstract

We present a high-quality sky segmentation model for depth refinement and investigate residual architecture performance to inform optimally shrinking the network. We describe a model that runs in near real-time on mobile device, present a new, highquality dataset, and detail a unique weighing to trade off false positives and false negatives in binary classifiers. We show how the optimizations improve bokeh rendering by correcting stereo depth misprediction in sky regions. We detail techniques used to preserve edges, reject false positives, and ensure generalization to the diversity of sky scenes. Finally, we present a compact model and compare performance of four popular residual architectures (ShuffleNet, MobileNetV2, Resnet-101, and Resnet-34-like) at constant computational cost.

Subject Areas :
Views 32
Downloads 4
 articleview.views 32
 articleview.downloads 4
  Cite this article 

Tyler Nuanes, Matt Elsey, Radek Grzeszczuk, John Paul Shen, "Sky Segmentation for Enhanced Depth Reconstruction and Bokeh Rendering with Efficient Architecturesin Proc. IS&T Int’l. Symp. on Electronic Imaging: Computational Imaging XVIII,  2020,  pp 378-1 - 378-7,  https://doi.org/10.2352/ISSN.2470-1173.2020.14.COIMG-378

 Copy citation
  Copyright statement 
Copyright © Society for Imaging Science and Technology 2020
72010604
Electronic Imaging
2470-1173
Society for Imaging Science and Technology
7003 Kilworth Lane, Springfield, VA 22151 USA