Single Image Haze Removal Using Dark Channel Prior (Supplementary Materials)

Paper ID: 877

¡¡

1. Additional results

(click to see full resolution image)

input haze image

our result

input haze image

our result

input haze image

our result

input haze image (from [2])

our result

input haze image (from [2])

our result

input haze image (from [2])

our result

 

2 . Intermediate results  and comparison

input haze image dark channel

transmission map before soft matting transmission map after soft matting

our result

transmission map of Fattal's technique [2] Fattal's result [2]

histogram equalization

¡¡

3. Comparison: Stadium

input haze image

Fattal's result [2]

Tan's result [1]

histogram equalization

our result

¡¡

4. Comparison: NYC 1

(Expect for our result and depth map, other images come from [3].)

input haze image

Fattal's result [2]

Tan's result [1]

Kopf et al's result [3]

our result

our depth map

¡¡

5. Comparisons: NYC 2

(Expect for our result and depth map, other images come from [3].)

input haze image

Fattal's result [2]

Tan's result [1]

Kopf et al's result [3]

our result

our depth map

¡¡

[1] R. Tan. Visibility in bad weather from a single image. CVPR, 2008 (http://www.commsp.ee.ic.ac.uk/~rtan/fog/index.html)

[2] R. Fattal. Single image dehazing. In SIGGRAPH, pages 1¨C9, 2008 (http://www.cs.huji.ac.il/~raananf/projects/defog/index.html)

[3] J. Kopf, B. Neubert, B. Chen, M. Cohen, D. Cohen-Or, O. Deussen, M. Uyttendaele, and D. Lischinski. Deep photo: Model-based photograph enhancement and viewing. SIGGRAPH Asia, 2008 (http://johanneskopf.de/publications/deep_photo/index.html)

¡¡

¡¡

¡¡