Skip to main content

FGC-VC: FLOW-GUIDED CONTEXT VIDEO COMPRESSION

Yiming Wang, Qian Huang, Bin Tang, Huashan Sun, Xiaotong Guo

  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00
Lecture 09 Oct 2023

Deep video compression has attracted more and more attention in recent years. Previous works rely on feature space operations, which may cause the offset maps overflow degrading reconstructed frame quality. In this work, we propose a flowguided module to guide the offset maps learning explicitly and alleviate offset maps overflow. Moreover, we introduce a context scheme to explore the temporal prior and fuse the hyper prior model to improve the compression ratio. For coding speed, we drop the time-consuming auto regressive module. Experimental results demonstrate that our method outperforms the previous learning-based schemes and traditional codecs. Compared to x265 with medium preset, our approach brings average 38.53% and 54.67% bit rate savings in PSNR and MS-SSIM metrics, respectively.