3D displays have various aspect ratios (e.g., 16:9, 4:3, and 3:2). Watching 3D videos with the wrong aspect ratio decreases the quality of the viewing experience. We have developed a smart reframing solution that uses a visual attention model for stereoscopic 3D video to identify the prominent visual regions of every stereoscopic frame. Our method uses several saliency indicators such as depth, edges, brightness, color, and movement. Additionally, our method provides a dynamic cropping window that slides smoothly from frame to frame.
Published in:
3DTV-Conference: The True Vision - Capture, Transmission and Display of 3D Video (3DTV-CON), 2012
Date of Conference: 15-17 Oct. 2012