A single two dimensional (2D) image does not contain depth information. An infinite number of points in the three dimensional (3D) space are projected to the same point in the image plane. But a single 2D image has some monocular depth cues, by which we can make a hypothesis of depth variation in the image to generate a depth map. This paper proposes an interactive method of depth map generatio...

Following another person’s gaze in order to achieve joint attention is an important skill in human social interactions. This paper analyzes the gaze following problem and proposes a learning-based computational model for the emergence of gaze following skills in infants. The model acquires advanced gaze following skills by learning associations between caregiver head poses and positions in spac...

A lot of work has been done extracting depth from image sequences, and relatively less has been done using only single images. Very little has been done merging these together. This paper describes the fusing of depth estimation from two images, with monocular cues. The paper will provide an overview of the stereo algorithm, and the details of fusing the stereo range data with monocular image f...

The provision of stereo images to facilitate depth perception by stereopsis is one key aspect of many Virtual Reality installations and there are many technical approaches to do so. However, differences in visual capabilities of the user and technical limitations of a specific set-up might restrict the spatial range in which stereopsis can be facilitated. In this paper, we transfer an existent ...

Vergence eye movements are a key factor in stereoscopic depth perception. In this brief review I will outline work at York University on select aspects of the relation between vergence and stereopsis, sensory fusion and depth constancy.

We introduce a digital hologram generation of a real 3D object captured by a depth camera. The depth camera is employing a time multiplexed concept for color and depth image acquisition in a single chip sensor. The 3D information, point cloud, corresponding to the real scene, is extracted from taken image pairs, a gray texture and a depth map by a depth camera. The extracted point cloud is used...

In this paper we will present the concept of a modular three dimensional broadcast chain, that allows for an evolutionary introduction of depth perception into the context of 2D digital TV. The work is performed within the framework of the European Information Society Technologies (IST) project “Advanced Three-dimensional Television System Technologies” (ATTEST), bringing together the expertise...

In this paper, we present a system to redistribute computational power in plane sweeping. Plane sweeping allows the generation of novel viewpoints of a scene by testing different depth hypotheses across input cameras. Typical plane sweeping approaches incorporate a uniform depth plane distribution to investigate different depth hypotheses to generate a depth map. When the scene consists of a sp...

Multiview video in “texture-plus-depth” format enables decoder to synthesize freely chosen intermediate views for enhanced visual experience. Nevertheless, transmission of multiple texture and depth maps over bandwidthconstrained and loss-prone networks is challenging, especially for conferencing applications with stringent deadlines. In this paper, we examine the problem of loss-resilient codi...