arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2302.02014eess.IV
收藏

屏幕内容图像编码的多任务学习

Multi-Task Learning for Screen Content Image Coding

Rashid Zamanshoar Heris, Ivan V. Bajić

摘要:

随着远程工作和协作的兴起,屏幕内容图像(SCI)的压缩变得越来越重要。虽然有用于自然图像的高效编解码器,以及用于纯合成图像的编解码器,但那些包含合成和自然内容的SCI构成了一个特殊的挑战。在本文中,我们提出了一个基于学习的图像编码模型开发的SCI。通过训练编码器提供适合两个任务的潜在表示-输入重建和合成/自然区域分割-我们创建了一个有效的SCI图像编解码器,其强大的性能通过实验验证。一旦训练完成,就不需要使用第二个任务(分割);编解码器仍然受益于分割友好的潜在表示。

英文摘要:

With the rise of remote work and collaboration, compression of screen content images (SCI) is becoming increasingly important. While there are efficient codecs for natural images, as well as codecs for purely-synthetic images, those SCIs that contain both synthetic and natural content pose a particular challenge. In this paper, we propose a learning-based image coding model developed for such SCIs. By training an encoder to provide a latent representation suitable for two tasks -- input reconstruction and synthetic/natural region segmentation -- we create an effective SCI image codec whose strong performance is verified through experiments. Once trained, the second task (segmentation) need not be used; the codec still benefits from the segmentation-friendly latent representation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑