通过可调变换使学习型图像编解码器适配屏幕内容
Adapting Learned Image Codecs to Screen Content via Adjustable Transformations
AI总结:
本文提出在保持基线学习型图像编解码器兼容性的前提下,引入可逆线性变换和预/后滤波网络,实现屏幕内容压缩最高10%码率节省且仅增加1%参数。
摘要:
随着学习型图像编解码器(LIC)日益普及,其对分布外数据的低编码效率成为某些应用的瓶颈。为了在不破坏向后兼容性的前提下提升 LIC 对屏幕内容(SC)图像的编码性能,我们提出在不改变底层基线编解码器操作流程的情况下,将参数化且可逆的线性变换引入编码流水线。我们设计了两个神经网络,分别作为预滤波器和后滤波器,以提高编码效率并帮助从编码伪影中恢复。我们端到端训练的解决方案在 SC 压缩上相比基线 LIC 实现了最高 10% 的码率节省,同时仅引入 1% 的额外参数。
英文摘要:
As learned image codecs (LICs) become more prevalent, their low coding efficiency for out-of-distribution data becomes a bottleneck for some applications. To improve the performance of LICs for screen content (SC) images without breaking backwards compatibility, we propose to introduce parameterized and invertible linear transformations into the coding pipeline without changing the underlying baseline codec's operation flow. We design two neural networks to act as prefilters and postfilters in our setup to increase the coding efficiency and help with the recovery from coding artifacts. Our end-to-end trained solution achieves up to 10% bitrate savings on SC compression compared to the baseline LICs while introducing only 1% extra parameters.
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。