This paper proposes a novel depth-aware salient object detection and segmentation framework via multiscale discriminative saliency fusion (MDSF) and bootstrap learning for RGBD images (RGB color images with corresponding Depth maps) and stereoscopic images. By exploiting low-level feature contrasts, mid-level feature weighted factors and high-level location priors, various saliency measures on four classes of features are calculated based on multiscale region segmentation. A random forest regressor is learned to perform the discriminative saliency fusion (DSF) and generate the DSF saliency map at each scale, and DSF saliency maps across multiple scales are combined to produce the MDSF saliency map. Furthermore, we propose an effective bootstrap learning-based salient object segmentation method, which is bootstrapped with samples based on the MDSF saliency map and learns multiple kernel support vector machines. Experimental results on two large datasets show how various categories of features contribute to the saliency detection performance and demonstrate that the proposed framework achieves the better performance on both saliency detection and salient object segmentation.
This paper introduces a novel framework for examplar-based inpainting. It consists in performing first the inpainting on a coarse version of the input image. A hierarchical super-resolution algorithm is then used to recover details on the missing areas. The advantage of this approach is that it is easier to inpaint low-resolution pictures than high-resolution ones. The gain is both in terms of computational complexity and visual quality. However, to be less sensitive to the parameter setting of the inpainting method, the low-resolution input picture is inpainted several times with different configurations. Results are efficiently combined with a loopy belief propagation and details are recovered by a single-image super-resolution algorithm. Experimental results in a context of image editing and texture synthesis demonstrate the effectiveness of the proposed method. Results are compared to five state-of-the-art inpainting methods.
Overt visual attention is the act of directing the eyes toward a given area. These eye movements are characterised by saccades and fixations. A debate currently surrounds the role of visual fixations. Do they all have the same role in the free viewing of natural scenes? Recent studies suggest that at least two types of visual fixations exist: focal and ambient. The former is believed to be used to inspect local areas accurately, whereas the latter is used to obtain the context of the scene. We investigated the use of an automated system to cluster visual fixations in two groups using four types of natural scene images. We found new evidence to support a focal-ambient dichotomy. Our data indicate that the determining factor is the saccade amplitude. The dependence on the low-level visual features and the time course of these two kinds of visual fixations were examined. Our results demonstrate that there is an interplay between both fixation populations and that focal fixations are more dependent on low-level visual features than are ambient fixations.