Subjective Evaluation of Stereoscopic Crosstalk Perception

While the causes and nature of crosstalk, as well as crosstalk reduction techniques have been extensively studied, it is still difficult to eliminate. Perceptually, crosstalk is one of the most annoying distortions in the visualization stage of stereoscopic imaging. Therefore, to understand how users perceive crosstalk is of fundamental importance to improve the quality of 3D presentations. In this paper, we aim at analyzing the impact of crosstalk level, camera baseline and scene content on users' perception of crosstalk. Extensive subjective tests are conducted and the opinion scores are statistically analyzed and discussed. The results indicate that crosstalk level, camera baseline, as well as scene content all have major impacts on the perception of crosstalk. We also show that these three factors correlate with each other in terms of impact on the crosstalk perception. Furthermore, we propose a content descriptor for crosstalk perception (CDCP) and show its effectiveness.