A Cloud 3D Dataset and Application-Specific Learned Image Compression in Cloud 3D
A Cloud 3D Dataset and Application-Specific Learned Image Compression in Cloud 3D
复制标题
DOI：
10.1007/978-3-031-19839-7_16
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Tianyi Liu;Sen He;V. Jayakumar;Wei Wang
中科院分区：
文献类型：
--
作者：
Tianyi Liu;Sen He;V. Jayakumar;Wei Wang
在Cloud 3D中，例如云游戏和云虚拟现实（VR），图像帧在云端进行渲染和压缩（编码），然后发送到客户端供用户查看。对于低延迟和高图像质量，优选快速、高压缩率和高质量的图像压缩技术。本文探讨了学习图像压缩的计算时间减少技术，使其更适合云 3D。更具体地说，我们采用了精简（低复杂性）和特定于应用程序的人工智能模型来减少计算时间，而不会降低图像质量。我们的方法基于两个关键见解：(1) 由于 3D 应用程序生成的帧是高度同质的，因此特定于应用程序的压缩模型可以提高通用模型的率失真性能； (2) 许多来自 3D 应用程序的计算机生成的帧比自然照片复杂，这使得降低模型复杂性以加速压缩计算成为可能。我们在六个游戏图像数据集上评估了我们的模型。结果表明，我们的方法具有与最先进的学习图像压缩算法类似的率失真性能，同时获得约 5 倍到 9 倍的加速，并将压缩时间减少到小于 1 秒（0.74 秒），使学习图像压缩更接近于云 3D 的可行性。代码可在 https://github.com/cloud-graphics-rendering/AppSpecificLIC 获取。
In Cloud 3D, such as Cloud Gaming and Cloud Virtual Reality (VR), image frames are rendered and compressed (encoded) in the cloud, and sent to the clients for users to view. For low latency and high image quality, fast, high compression rate, and high-quality image compression techniques are preferable. This paper explores computation time reduction techniques for learned image compression to make it more suitable for cloud 3D. More specifically, we employed slim (low-complexity) and application-specific AI models to reduce the computation time without degrading image quality. Our approach is based on two key insights: (1) as the frames generated by a 3D application are highly homogeneous, application-specific compression models can improve the rate-distortion performance over a general model; (2) many computer-generated frames from 3D applications are less complex than natural photos, which makes it feasible to reduce the model complexity to accelerate compression computation. We evaluated our models on six gaming image datasets. The results show that our approach has similar rate-distortion performance as a state-of-the-art learned image compression algorithm, while obtaining about 5x to 9x speedup and reducing the compression time to be less than 1 s (0.74s), bringing learned image compression closer to being viable for cloud 3D. Code is available at https://github.com/cloud-graphics-rendering/AppSpecificLIC.