PERCEPTUAL QUALITY ASSESSMENT ON DIBR SYNTHESIZED VIDEOS WITH COMPOSITE DISTORTIONS

DIBR (depth-image-based rendering) synthesized videos has becomes increasingly popular recently in supporting 3D-TV, Free-viewpoint video (FVV) and interactive graphic applica- tions. Due to the synthesis process, it contains composite dis- tortions, i.e., DCT-like distortions plus geometric distortions. This has led to new challenges for the development of subjec- tive and objective video quality assessment (VQA) models, which have not taken such composite distortions into con- sideration. In this work, we construct a new database com- posed of DIBR synthesized videos, the reference view video is compressed by H.264 and HEVC encoders, which is sub- sequently synthesized to the virtual view with different DIBR algorithms. We also proposed a novel no-reference (NR) syn- thesized video quality metric with multi-modal feature pool- ing and evaluate it against representative full reference (FR) and NR objective VQA models on the proposed database. The database and the proposed metric will be made available to the public.