Ghost-Free High Dynamic Range Imaging via Rank Minimization
Authors:
- 13 May 2014
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 21 (9) , 1045-1049
Abstract
We propose a ghost-free high dynamic range (HDR) image synthesis algorithm using a low-rank matrix completion framework, which we call RM-HDR. Based on the assumption that irradiance maps are linearly related to low dynamic range (LDR) image exposures, we formulate ghost region detection as a rank minimization problem. We incorporate constraints on moving objects, i.e., sparsity, connectivity, and priors on under- and over-exposed regions into the framework. Experiments on real image collections show that the RM-HDR can often provide significant gains in synthesized HDR image quality over state-of-the-art approaches. Additionally, a complexity analysis is performed which reveals computational merits of RM-HDR over recent advances in deghosting for HDR.Keywords
Funding Information
- Office of Naval Research (N00014-12-1-0765)
This publication has 23 references indexed in Scilit:
- High dynamic range imaging by a rank-1 constraint2013
- HDR Deghosting: How to Deal with Saturation?2013
- Moving Object Detection by Detecting Contiguous Outliers in the Low-Rank RepresentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- Ghost detection and removal for high dynamic range images: Recent advancesSignal Processing: Image Communication, 2012
- Gradient-Directed Multiexposure CompositionIEEE Transactions on Image Processing, 2011
- Robust principal component analysis?Journal of the ACM, 2011
- PatchMatchACM Transactions on Graphics, 2009
- Artifact-free High Dynamic Range imaging2009
- Automatic High-Dynamic Range Image Generation for Dynamic ScenesIEEE Computer Graphics and Applications, 2008
- Recovering high dynamic range radiance maps from photographs1997