000188639 001__ 188639
000188639 005__ 20190331192702.0
000188639 0247_ $$2doi$$a10.1109/ICIP.2013.6738487
000188639 037__ $$aCONF
000188639 245__ $$aNear-Infrared Guided Color Image Dehazing
000188639 269__ $$a2013
000188639 260__ $$c2013
000188639 336__ $$aConference Papers
000188639 500__ $$aReceived one of the three Best (Open) Paper Awards given at the conference.
000188639 520__ $$aNear-infrared (NIR) light has stronger penetration capability than visible light due to its long wavelength, thus being less scattered by particles in the air. This makes it desirable for image dehazing to unveil details of distant objects in landscape photographs. In this paper, we propose an improved image dehazing scheme using a pair of color and NIR images, which effectively estimates the airlight color and transfers details from the NIR. A two-stage dehazing method is proposed by exploiting the dissimilarity between RGB and NIR for airlight color estimation, followed by a dehazing procedure through an optimization framework. Experiments on captured haze images show that our method can achieve substantial improvements on the detail recovery and the color distribution over the existing image dehazing algorithms.
000188639 6531_ $$aNear-infrared
000188639 6531_ $$aDehazing
000188639 6531_ $$aAirlight Color
000188639 6531_ $$aRGB images
000188639 6531_ $$aOptimization
000188639 700__ $$aFeng, Chen
000188639 700__ $$aZhuo, Shaojie
000188639 700__ $$aZhang, Xiaopeng
000188639 700__ $$aShen, Liang
000188639 700__ $$0241946$$aSüsstrunk, Sabine$$g125681
000188639 7112_ $$aIEEE 20th International Conference on Image Processing (ICIP)$$cMelbourne, Australia$$dSeptember 15-18, 2013
000188639 773__ $$q2363-2367$$tProc. IEEE 20th International Conference on Image Processing (ICIP)
000188639 8564_ $$s15202256$$uhttps://infoscience.epfl.ch/record/188639/files/ImageDehazing_icip2013.pdf$$yn/a$$zn/a
000188639 8564_ $$s2681064$$uhttps://infoscience.epfl.ch/record/188639/files/poster_icip_2013.pdf$$yposter$$zposter
000188639 909C0 $$0252320$$pIVRL$$xU10429
000188639 909CO $$ooai:infoscience.tind.io:188639$$pconf$$pIC$$qGLOBAL_SET
000188639 917Z8 $$x125681
000188639 917Z8 $$x125681
000188639 917Z8 $$x125681
000188639 917Z8 $$x125681
000188639 917Z8 $$x125681
000188639 917Z8 $$x125681
000188639 937__ $$aEPFL-CONF-188639
000188639 973__ $$aEPFL$$rREVIEWED$$sPUBLISHED
000188639 980__ $$aCONF