论文信息 - An Image Compression Framework with Learning-based Filter

An Image Compression Framework with Learning-based Filter

In this paper, a coding framework VIP-ICT-Codec is introduced. Our method is based on the VTM (Versatile Video Coding Test Model). First, we propose a color space conversion from RGB to YUV domain by using a PCA-like operation. A method for the PCA mean calculation is proposed to de-correlate the residual components of YUV channels. Besides, the correlation of UV components is compensated considering that they share the same coding tree in VVC. We also learn a residual mapping to alleviate the over-filtered and under-filtered problem of specific images. Finally, we regard the rate control as an unconstraint Lagrangian problem to reach the target bpp. The results show that we achieve 32.625dB at the validation phase.

[1] David Minnen,et al. Variational image compression with a scale hyperprior , 2018, ICLR.

[2] Ming Li. VimicroABCnet: An Image Coder Combining A Better Color Space Conversion Algorithm and A Post Enhancing Network , 2019, CVPR Workshops.

[3] Jiro Katto,et al. Deep Residual Learning for Image Compression , 2019, CVPR Workshops.

[4] Ming Li. A Better Color Space Conversion Based on Learned Variances For Image Compression , 2019, CVPR Workshops.

[5] Zhan Ma,et al. Learned Image Restoration for VVC Intra Coding , 2019, CVPR Workshops.

[6] Lei Zhou,et al. End-to-end Optimized Image Compression with Attention Mechanism , 2019, CVPR Workshops.

[7] Jiro Katto,et al. Dual Learning-based Video Coding with Inception Dense Blocks , 2019, 2019 Picture Coding Symposium (PCS).

[8] Lei Zhou,et al. Variational Autoencoder for Low Bit-rate Image Compression , 2018, CVPR Workshops.

[9] Eirikur Agustsson,et al. NTIRE 2017 Challenge on Single Image Super-Resolution: Dataset and Study , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).