Inverse-tone-mapped HDR video quality assessment: A new dataset and benchmark

Leidong Fan, Ao Yang, Cheng Guo, Xiuhua Jiang, Yixuan Gao, Xiongkuo Min

Abstract: Highlights•The first inverse-tone-mapped HDR video quality assessment dataset was established. The dataset is called “VQA4ITM”, which is an acronym for “Video Quality Assessment for Inverse Tone Mapping”.•Benchmark experiments were conducted on the VQA4ITM dataset to assess the effectiveness of existing quality assessment methods in assessing inverse-tone-mapped videos (ITMVs). The results revealed that the existing VQA methods did not perform satisfactorily on the VQA4ITM dataset.•The distortions were classified and examined from a human perspective to provide a basis for the development of more effective VQA algorithms for quality assessment of ITMVs.