Evaluating Methods for Controlling Depth Perception inStereoscopic Cinematography

摘要

Existing stereoscopic imaging algorithms can create static stereoscopic images with perceived depth controlfunction to ensure a compelling 3D viewing experience without visual discomfort. However, current algorithmsdo not normally support standard Cinematic Storytelling techniques. These techniques, such as object movement,camera motion, and zooming, can result in dynamic scene depth change within and between a series of frames(shots) in stereoscopic cinematography. In this study, we empirically evaluate the following three types ofstereoscopic imaging approaches that aim to address this problem. (1) Real-Eye Configuration: set camera separation equal to the nominal human eye interpupillary distance.The perceived depth on the display is identical to the scene depth without any distortion. (2) Mapping Algorithm:map the scene depth to a predefined range on the display to avoid excessive perceived depth. A new methodthat dynamically adjusts the depth mapping from scene space to display space is presented in addition to anexisting fixed depth mapping method. (3) Depth of Field Simulation: apply Depth of Field (DOF) blur effectto stereoscopic images. Only objects that are inside the DOF are viewed in full sharpness. Objects that are faraway from the focus plane are blurred. We performed a human-based trial using the ITU-R BT.500-11 Recommendation to compare the depthquality of stereoscopic video sequences generated by the above-mentioned imaging methods. Our results indicatethat viewers' practical 3D viewing volumes are different for individual stereoscopic displays and viewers cancope with much larger perceived depth range in viewing stereoscopic cinematography in comparison to staticstereoscopic images. Our new dynamic depth mapping method does have an advantage over the fixed depthmapping method in controlling stereo depth perception. The DOF blur effect does not provide the expectedimprovement for perceived depth quality control in 3D cinematography. We anticipate the results will be ofparticular interest to 3D filmmaking and real time computer games.