Compressed Domain Prior-Guided Video Super-Resolution for Cloud Gaming Content

2025-01-03

AI Summary

To address severe blocking artifacts, ringing distortions, and edge-detail loss in cloud gaming video super-resolution, this paper proposes a lightweight and efficient reconstruction method. The approach introduces three key innovations: (1) a novel encoding prior-guided mechanism that jointly incorporates H.264/AVC quantization parameters and motion information as structural constraints; (2) a compression-domain guided block (CDGB) and a patch-wise focal frequency-domain loss, explicitly modeling compression distortion distributions and enhancing high-frequency fidelity; and (3) a low-parameter architecture built upon U-Net and reparameterized reconstruction modules. Evaluated on a dedicated cloud gaming dataset, the method achieves significantly higher PSNR and SSIM than state-of-the-art methods including EDSR and RCAN, while maintaining only 1.18 million parameters—enabling real-time, low-latency deployment on resource-constrained end devices.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Learning on the Edge & Model Compression
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Economic aspects and information design of Web, GenAI, and cloud computing
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Cloud gaming is an advanced form of Internet service that necessitates local terminals to decode within limited resources and time latency. Super-Resolution (SR) techniques are often employed on these terminals as an efficient way to reduce the required bit-rate bandwidth for cloud gaming. However, insufficient attention has been paid to SR of compressed game video content. Most SR networks amplify block artifacts and ringing effects in decoded frames while ignoring edge details of game content, leading to unsatisfactory reconstruction results. In this paper, we propose a novel lightweight network called Coding Prior-Guided Super-Resolution (CPGSR) to address the SR challenges in compressed game video content. First, we design a Compressed Domain Guided Block (CDGB) to extract features of different depths from coding priors, which are subsequently integrated with features from the U-net backbone. Then, a series of re-parameterization blocks are utilized for reconstruction. Ultimately, inspired by the quantization in video coding, we propose a partitioned focal frequency loss to effectively guide the model's focus on preserving high-frequency information. Extensive experiments demonstrate the advancement of our approach.

Problem

• Cloud Gaming
• Super Resolution
• Image Compression Artifact

Innovation

• CPGSR Lightweight Network
• Compression Artifact Reduction
• Enhanced Loss Function