Sort:
Regular Paper Issue
Artistic Augmentation of Photographs with Droplets
Journal of Computer Science and Technology 2019, 34(6): 1294-1306
Published: 22 November 2019
Abstract Collect

Artistic augmentation of photographs with water droplets aims at generating aesthetic yet realistic images, and thus differs from traditional augmented reality in two aspects. One difference lies in the adoption of a new image as the environment map in order to render reflected or refracted effects on the surface of inserted water droplets. The other difference is in modeling of water droplets including hanging droplets and resting droplets. These differences raise two research challenges: 1) how to adjust the brightness and colors of the new environment map to maintain visual consistency between the new environment map and the original input image; 2) how to model hanging and resting droplets aesthetically. This paper proposes a framework that addresses these two challenges and demonstrates the effectiveness of our framework by generating example augmented images.

Open Access Research Article Issue
A computational model of topological and geometric recovery for visual curve completion
Computational Visual Media 2016, 2(4): 329-342
Published: 30 May 2016
Abstract PDF (2.6 MB) Collect
Downloads:99

Visual curve completion is a fundamental problem in understanding the principles of the human visual system. This problem is usually divided into two problems: a grouping problem and a shape problem. On one hand, though perception of the visually completed curve is clearly a global task (for example, a human perceives the Kanizsa triangle only when seeing all three black objects), conventional methods for solving the grouping problem are generally based on local Gestalt laws. On the other hand, the shape of the visually completed curve is usually recovered by minimizing shape energy in existing methods. However, not only do these methods lack mechanisms to adjust the shape of the recovered visual curve using perceptual, psychophysical, and neurophysiological knowledge, but it is also difficult to calculate an explicit representation of the visually completed curve. In this paper, we present a systematic computational model for generating a visually completed curve. Firstly, based on recent studies of perception, psychophysics, and neurophysiology, we formulate a grouping procedure based on the human visual system by seeking a minimum Hamiltonian cycle in a graph, solving the grouping problem in a global manner. Secondly, we employ a Bézier curve-based model to represent the visually completed curve. Not only is an explicit representation deduced, but we also present a means to integrate knowledge from related areas, such as perception, psychophysics, and neurophysiology, and so on. The proposed computational model has been validated using many modal and amodal completion examples, and desirable results were obtained.

Total 2