Quality assessment of 3D video in rate allocation experiments

In this contribution, we address the problem of measuring and optimizing the visual quality of encoded 3D video. The 3D video is represented in the format of monoscopic color video augmented by per-pixel depth map and then encoded with H.264 encoder. To optimize the encoding performance we test different bit budgets for the color video and the depth and measure the quality by virtual view quality metrics. Small-scale subjective tests supplement the objective measurements. The obtained results show that, for similar overall quality numbers, observers favorably trade off lower depth quality for higher color quality and that depth distortions are perceived but considered less significant than the color distortions.