3D Visual Discomfort Assessment Considering Optical And Neural Attention Models

Amidst the advancement of stereoscopic 3D(S3D)multimedia services,the experience of 3D display outperforms the traditional 2D through depth perception.In order to provide users with higher quality of experience,it is urgently needed to establish efficient visual comfort assessment metrics for stereoscopic images,which is helpful to the optimization of 3D image/video system.We introduce a new objective assessment method for visual discomfort of stereoscopic images by using neural attention mechanism.Mainly inspired by the visual feedback mechanism of visual attention,traditional visual comfort assessment(VCA)metrics find the salient region in the images and then use the disparity value of the objects in this region to construct the VCA model.Although the previous methods are promising in VCA,they are insufficient,since these techniques work effectively only when the salient regions of scene coincide with the largest disparity regions.In this paper,we study objects with large disparities but not in the salient regions.We find that large disparities at non-salient regions make human uncomfortable.According to this,a new 3D non-salient map is built.Then,the effect of image size on visual discomfort is depicted by applying multi-scale theory.Besides,we find factors affecting visual comfort along the visual pathways.The statistics data used for the 3D visual visual comfort assessment(3D-VCA)model extracted from the traditional optical statistical elements derived,retinal disparity and neurophysiological elements obtained from V1 and MT areas.These physiological statistics are used to create a new feature map for 3D-VCA models,known as MT importance map.The thirteen typical MT neurons are divided into four kinds of cells: tuned-excitatory cells,tuned-inhibitory cells,far cells and near cells based on their characteristics.Disparity map is also transformed by changing the viewing distance in the formula to calculate the horizontal angular disparity factor.We propose that variation of viewing distance will make the MT cells more intense reaction.As a result,three types of angular disparity maps are obtained: tuned-near,tuned-far and original disparity maps.Preliminary results on two public available databases exhibit the performance of the proposed approach outperforms previous S3 D VCA models.