On the selection of residual formula for HDR video coding

High Dynamic Range (HDR) videos are commonly compressed using existing Low Dynamic Range (LDR) coding standards. This necessarily implies a Tone Mapping (TM) stage which aims at reducing the input video range while preserving the most significant scene details. In most cases, a residual sequence is encoded and used at the decoder side to recover the HDR content. The challenge is to efficiently encode both LDR sequences (TM and residual) without compromising the quality of the reconstructed video. Furthermore, the choice of the residual sequence can have an important impact on the HDR video coder performances. In this work, we aim to study and analyse different approaches for residual determination. The performance is discussed in terms of entropy of the residual and video coding. Objective assessments show that differential residual presents much higher efficiency than ratio residuals in terms of bandwidth saving and HDR reconstruction quality.