2023/02/18 by Fangzheng Lin, Heming Sun, Lin, Fangzheng +5 · 2 citations
Computer Science · #Advanced Data Compression Techniques #Advanced Image and Video Retrieval Techniques #Algorithms and Data Compression #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2302.09263
openalex publication_date 2023/02/18 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Recent state-of-the-art Learned Image Compression methods feature spatial context models, achieving great rate-distortion improvements over hyperprior methods. However, the autoregressive context model requires serial decoding, limiting runtime performance. The Checkerboard context model allows parallel decoding at a cost of reduced RD performance. We present a series of multistage spatial context models allowing both fast decoding and better RD performance. We split the latent space into square patches and decode serially within each patch while different patches are decoded in parallel. The proposed method features a comparable decoding speed to Checkerboard while reaching the RD performance of Autoregressive and even also outperforming Autoregressive. Inside each patch, the decoding order must be carefully decided as a bad order negatively impacts performance; therefore, we also propose a decoding order optimization algorithm.