Elic: Efficient learned image compression with unevenly grouped space-channel contextual adaptive coding

Dailan He, Ziming Yang, Weikun Peng, Rui Ma, Hongwei Qin, Yan Wang

Abstract: Recently, learned image compression techniques have achieved remarkable performance, even surpassing the best manually designed lossy image coders. They are promis- ing to be large-scale adopted. For the sake of practical- ity, a thorough investigation of the architecture design of learned image compression, regarding both compression performance and running speed, is essential. In this pa- per, we first propose uneven channel-conditional adaptive coding, motivated by the observation of energy compaction in learned image compression. Combining the proposed uneven grouping model with existing context models, we obtain a spatial-channel contextual adaptive model to im- prove the coding performance without damage to running speed. Then we study the structure of the main transform and propose an efficient model, ELIC, to achieve state-of- the-art speed and compression ability. With superior per- formance, the proposed model also supports extremely fast preview decoding and progressive decoding, which makes the coming application of learning-based image compres- sion more promising.