In　High　Efficiency　Video　Coding　(HEVC),　a　rate　control　module　usually　relies　on　a　bitrate　model　(representing　the　bitrate　as　a　function　of　video　content　statistics　and　control　parameters　of　the　codec)　to　control　the　encoder　to　achieve　the　target　bitrate.　Existing　bitrate　models　are　not　accurate　due　to　their　sensitivity　to　dynamic　change　of　video　content.　To　address　this　limitation,　this　paper　proposes　a　new　bitrate　model,　which　represents　the　bit　rate　of　motion-compensated　residual　as　a　function　of　the　statistics　of　Mean　Absolute　Partial　Transformed　Difference　(MAPTD)　of　video　content　and　Lagrange　multiplier　λ　specifically,　we　observe　that　at　the　coefficient　group　level,　the　relationship　between　the　bitrate　and　MAPT-D　is　stable　against　the　variation　of　coding　unit　(CU)　size,　transform　unit　(TU)　size,　image　resolution　and　content.　Experimental　results　show　that　our　model　can　achieve　superior　performance　in　frame-level　residue-bit-rate　estimation,　compared　with　state-of-the-art　bitrate　models.　©　2017　IEEE.