Attention-based high dynamic range imaging

 

         

Typical response of a visual neuron

Attention Map

Attention Only

Adaptation Only

Both

   

 

Overview

 

Many tone mapping algorithms have been proposed based on the studies in Human Visual System; however, they rarely addressed the effects of attention to contrast response. As attention plays an important role in human visual system, we proposed a local tone mapping method that respects both attention and adaptation effects. We adopt the High Dynamic Range (HDR) saliency map to compute an attention map, which predicts the attentive regions and nonattentative regions in an HDR image. The attention map is then used to locally adjust the contrast of the HDR image according to attention and adaptation models found in psychophysics. We applied our tone mapping approach to HDR images and videos and compared with the results generated by three state-of-the-art tone mapping algorithms. Our experiments show that our approach produces results with better image quality in terms of preserving details and chromaticity of visual saliency.

 

Publications

 

·        Wen-Chieh Lin and Zhi-Cheng Yan, “Attention-based High Dynamic Range Imaging,” The Visual Computer, Vol. 27, No. 6, 2011, pp. 717-727.

 

Results of HDR Images and HDR Videos

 

1. Comparison with other approaches on HDR Images:

 

Histogram adjustment

Optimization tone mapping

 

 

 

 

Photographic tone reproduction

Our approach

 

 

Histogram adjustment

 

 

Optimization tone mapping

 

 

Photographic tone reproduction

 

 

Our approach

 

 

2. Comparison of our approach with the photographic tone reproduction approach on HDR Videos

(The original HDR videos are courtesy of Grzegorz Krawczyk)

Highway [divx avi]

Tunnel [divx avi]