Self Texture Transfer Networks for Low Bitrate Image Compression
Self Texture Transfer Networks for Low Bitrate Image Compression
复制标题
DOI：
10.1109/cvprw53098.2021.00214
复制
发表时间：
2021-06
期刊：
影响因子：
--
通讯作者：
Shoma Iwai;Tomo Miyazaki;Yoshihiro Sugaya;S. Omachi
中科院分区：
文献类型：
--
作者：
Shoma Iwai;Tomo Miyazaki;Yoshihiro Sugaya;S. Omachi
有损图像压缩会导致纹理的损失，特别是在低比特率时。为了缓解这个问题，我们提出了一种新的图像压缩方法，利用基于参考的图像超分辨率模型。我们使用了两种图像压缩模型和一种自纹理传输模型。图像压缩模型对整个输入图像和所选择的参考块进行编码和解码。参考块较小，但压缩质量较高。自纹理传递模型将参考块的纹理传递到压缩图像中的相似区域。实验结果表明，该方法通过对参考块纹理的转移，可以重建出精确的纹理。
Lossy image compression causes a loss of texture, especially at low bitrate. To mitigate this problem, we propose a novel image compression method that utilizes a reference-based image super-resolution model. We use two image compression models and a self texture transfer model. The image compression models encode and decode a whole input image and selected reference patches. The reference patches are small but compressed with high quality. The self texture transfer model transfers the texture of reference patches into similar regions in the compressed image. The experimental results show that our method can reconstruct accurate texture by transferring the texture of reference patches.