发表机构
Purdue University（普渡大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出一种基于可变形二维高斯泼溅的实时视频压缩框架，以粗到细多尺度结构表示GOP，在LPIPS上超越H.265等先进方法，实现高效4K视频压缩。
AI 中文摘要
超高清（UHD）视频对高效存储和实时解码提出了重大挑战。基于学习的方法，如神经视频压缩（NVC）和隐式神经表示（INR），实现了有竞争力的率失真性能，但存在高解码延迟和过多内存使用的问题。与此同时，高斯泼溅因其超快速渲染和高保真视觉质量，近期在计算机图形学界引起了关注。尽管有这些优势，其在视频压缩中的应用仍 largely 未被探索。为弥合这一差距，我们提出了一种实时视频压缩框架，该框架使用由粗到细的多尺度二维高斯泼溅（2DGS）结构，并结合轻量级形变网络，来表示和压缩一组图片（GOP）。实验表明，我们的方法在LPIPS指标上的率失真性能超越了H.265和其他最先进的基于学习的视频压缩方法。我们的工作展示了高斯泼溅作为高效高分辨率视频压缩实用解决方案的潜力。
英文摘要
Ultra-High-Definition (UHD) video presents significant challenges for efficient storage and real-time decoding. Learning-based methods, such as Neural Video Compression (NVC) and Implicit Neural Representations (INR), achieve competitive rate-distortion performance but suffer from high decoding latency and excessive memory usage. Meanwhile, Gaussian Splatting has recently attracted attention in the computer graphics community due to its ultra-fast rendering and high-fidelity visual quality. Despite these advantages, its application in video compression remains largely unexplored. To bridge this gap, we propose a real-time video compression framework that represents and compresses a Group of Pictures (GOP) using a coarse-to-fine multi-scale 2D Gaussian Splatting (2DGS) structure coupled with a lightweight deformation network. Experiments demonstrate that our method delivers rate-distortion performance in LPIPS that surpasses H.265 and other state-of-the-art learning-based video compression methods. Our work demonstrates the potential of Gaussian Splatting as a practical solution for efficient high-resolution video compression.
