Implementation of an out-of-the loop post-processing technique for hevc decoded depth maps

When depth-maps are compressed using the existing video codecs, the compression artifacts introduce distortions in the rendered views. To get better rendering, it is important to get rid of these compression artifacts. The thesis achieves this by using a post-processing frame-work on HEVC decoded depth maps. The proposed method is based on compression artifact analysis of depth maps. It implements a post-processing filter frame-work with an edge-adaptive joint trilateral filter [43] which can effectively minimize the effects of compression artifacts from the HEVC decoded depth-maps. The rendered views before and after applying the post-processing filter are compared with respect to the perceptual quality of the rendered views. The PSNR, SSIM and an approximation of MOS are the quality metrics that are used for video quality estimation. Four different video sequences- Break-dancer, Ballet, Kendo and Balloons are used in the experiments. There is an improvement in PSNR as well as SSIM for the two sequences- Break-dancer and Ballet. Break-dancer sequence shows an improvement of 0.04 dB in PSNR and 0.006 dB in SSIM. Ballet shows an improvement of 0.553 dB in PSNR and 0.0031 dB in SSIM. There is no improvement in PSNR for Kendo sequence while the SSIM is constant (not much edge information). While for the balloons sequence, there is no improvement in either the PSNR or the SSIM. This can be attributed to the fact that the rendered views after post-processing have larger pixel differences with the original than those views rendered without applying any post-processing. However, the main improvement brought about by this method is in the perceptual quality of the rendered views. An approximate MOS test survey suggests that the views rendered after post-processing are always better perceptually compared to the ones rendered without post-processing. In this regard, all the four test sequences show an improvement in perceptual quality of the rendered views.