Julien Flack

Rapid 2D-to-3D conversion

The conversion of existing 2D images to 3D is proving commercially viable and fulfills the growing need for high quality stereoscopic images. This approach is particularly effective when creating content for the new generation of autostereoscopic displays that require multiple stereo images. The dominant technique for such content conversion is to develop a depth map for each frame of 2D material. The use of a depth map as part of the 2D to 3D conversion process has a number of desirable characteristics: 1. The resolution of the depth may be lower than that of the associated 2D image. 2. It can be highly compressed. 3. 2D compatibility is maintained. 4. Real time generation of stereo, or multiple stereo pairs, is possible. The main disadvantage has been the laborious nature of the manual conversion techniques used to create depth maps from existing 2D images, which results in a slow and costly process. An alternative, highly productive technique has been developed based upon the use of Machine Leaning Algorithm (MLAs). This paper describes the application of MLAs to the generation of depth maps and presents the results of the commercial application of this approach.

Low bandwidth stereoscopic image encoding and transmission

Encoding 3D information using depth maps is quickly becoming the dominant technique for rendering high quality stereoscopic images. This paper describes how depth maps can be highly compressed and transmitted alongside 2D images with minimal additional bandwidth. The authors have previously described a rapid 2D to 3D conversion system for generating depth maps. This system, which relies on Machine Learning algorithms, effectively encodes the relationships between a 2D source image and the associated depths of objects within the image. These relationships, which are expressed in terms of the colour and position of objects, may be exploited to provide an effective compression mechanism. This paper describes the practical implementation of this technology in an integrated 2D to 3D conversion system. We demonstrate the advantages of the encoding scheme relative to other industry standard compression techniques, examining issues relating to bandwidth, decoding performance and the effect of compression artifacts on stereoscopic image quality.

Temporally consistent virtual camera generation from stereo image sequences

The recent emergence of auto-stereoscopic 3D viewing technologies has increased demand for the creation of 3D video content. A range of glasses-free multi-viewer screens have been developed that require as many as 9 views generated for each frame of video. This presents difficulties in both view generation and transmission bandwidth. This paper examines the use of stereo video capture as a means to generate multiple scene views via disparity analysis. A machine learning approach is applied to learn relationships between disparity generated depth information and source footage, and to generate depth information in a temporally smooth manner for both left and right eye image sequences. A view morphing approach to multiple view rendering is described which provides an excellent 3D effect on a range of glasses-free displays, while providing robustness to inaccurate stereo disparity calculations.