Visual saliency, namely the perceptual significance to human vision system (HVS), is a quality that differentiates an object from its neighbors. Detection of salient regions which contain prominent features and represent main contents of the visual scene, has obtained wide utilization among computer vision based applications, such as object tracking and classification, region-of-interest (ROI) ...

We present an algorithm for computing the relative perceptual saliencies of the features of a three-dimensional object using either goodness-of-view scores measured at several viewpoints or perceptual similarities among several object views. This technique addresses the inverse, ill-posed version of the direct problem of predicting goodness-of-view scores or viewpoint similarities when the obje...

The saliency-based or bottom-up model of visual attention presented in this paper deals with still color images. The model we built is based on numerous properties of the human visual system (HVS), thus providing a biologically plausible system. The computation of early visual features such as color and orientation is a key step for any bottom-up model and the way to extract these visual featur...

High-quality space target images are important for surveillance and attack defense confrontation. To obtain with higher resolution sharpness, this paper proposes an image super-resolution reconstruction network based on dual regression a deformable convolutional attention mechanism (DCAM). Firstly, the mapping is constrained by regression; secondly, convolution used to expand perceptual field e...

Title of dissertation: PERCEPTUAL GRAPHICS FOR EFFECTIVE VISUALIZATION Chang Ha Lee, Doctor of Philosophy, 2005 Dissertation directed by: Professor Amitabh Varshney Department of Computer Science Current trends in 3D graphics point to a near future when our ability to generate 3D content will far surpass our ability to analyze it meaningfully. These trends have inspired us to improve the compre...

Computer vision applications often need to process only a representative part of the visual input rather than the whole image/sequence. Considerable research has been carried out into salient region detection methods based either on models emulating human visual attention (VA) mechanisms or on computational approximations. Most of the proposed methods are bottom-up and their major goal is to fi...

Facial features differ in the amount of expressive information they convey. Specifically, eyes are argued to be essential for fear recognition, while smiles are crucial for recognising happy expressions. In three experiments, we tested whether expression modulates the perceptual saliency of diagnostic facial features and whether the feature's saliency depends on the face configuration. Particip...

Viewpoint selection is an emerging area in computer graphics with applications in fields such as scene exploration, image-based modeling, and volume visualization. In particular, best view selection algorithms are used to obtain the minimum number of views (or images) in order to understand or model an object or scene better. In this paper, we present a unified framework for viewpoint selection...

In this paper we present proof-of-concept for a novel solution consisting of a short-term 3D memory for artificial attention systems, loosely inspired in perceptual processes believed to be implemented in the human brain. Our solution supports the implementation of multisensory perception and stimulus-driven processes of attention. For this purpose, it provides (1) knowledge persistence with te...