Attention-based high dynamic range imaging

Abstract

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.

Effect of tone mapping operators on visual attention deployment

“…Their focus has been the perceptual quality or visual appeal of the tone mapped images while this has paper focused on VA. We therefore believe that VA is a complimentary and crucial aspect (in addition to visual quality) for assessing the overall perceptual impacts of TMOs. Not surprisingly, a few recently developed [20][21] TMOs employ VA for dynamic range reduction. The method 20 by Mei et al uses the visual saliency map of the HDR and then use the saliency of the local regions to control the local tone mapping curve such that highly salient regions will have their details and contrast better protected so as to remain salient and attract visual attention in the tone mapped display.…”

Automated parameter tuning for tone mapping using visual saliency

“…Most systems are built on feature integration theory as outlined by Treisman and Gelade [40], whose core idea is to extract several types of features and combine their saliency to generate a saliency map [17]. Among all the current computational systems, the model proposed by Itti et al [23,22] is the best known and serves as the basis for many research projects [21,41,4,26]. Their approach predicts bottom up attention derived only from the visual scene in a static color image, combining multiple features, including intensity, color, and orientation, to produce saliency maps.…”

Change Blindness Images

“…Image regions receiving less visual attention may be rendered more approximately with larger errors [28]. Other properties of the human visual system, such as inattentional blindness and change blindness, have also been utilized for rendering acceleration [29], [30], [31], character animation [32], and tone mapping [33]. Perceptual strategies are also useful in participating media rendering [34], virtual crowd rendering [35], and rendering of motion blur effects [36].…”