[Zurück]


Zeitschriftenartikel:

T. Akhavan, H. Kaufmann:
"Backward compatible HDR stereo matching: a hybrid tone-mapping-based framework";
EURASIP Journal on Image and Video Processing, 36 (2015), S. 1 - 18.



Kurzfassung englisch:
Stereo matching under complex circumstances, such as low-textured areas and high dynamic range (HDR)
scenes is an ill-posed problem. In this paper we introduce a stereo matching approach for real world HDR
scenes which is backward compatible to conventional stereo matchers. For this purpose (i) we compare and
evaluate the tone-mapped disparity maps to nd the most suitable tone-mapping approach for the stereo
matching purpose. Thereof (ii) we introduce a combining graph-cut based framework for e ectively fusing the
tone-mapped disparity maps obtained from di erent tone-mapped input image pairs. And nally (iii) we
generate reference ground truth disparity maps for our evaluation using the original HDR images and a
customized stereo matching method for HDR inputs. Our experiments show that, combining the most e ective
features of tone-mapped disparity maps, an improved version of the disparity is achieved. Not only our results
reduce the Low Dynamic Range (LDR), conventional disparity errors by the factor of three, but also,
outperform the other well known tone-mapped disparities by providing the closest results to the original HDR
disparity maps.

Schlagworte:
Tone Mapping; Stereo Matching; Disparity Map; Low Dynamic Range; High Dynamic Range; Markov Random Field; Graph Cut


"Offizielle" elektronische Version der Publikation (entsprechend ihrem Digital Object Identifier - DOI)
http://dx.doi.org/10.1186/s13640-015-0092-3

Elektronische Version der Publikation:
http://www.jivp.eurasipjournals.com/content/2015/1/36


Erstellt aus der Publikationsdatenbank der Technischen Universität Wien.