Deformable 2D Gaussian Splatting for Efficient 4K Video Compression

2026-09-12

AI Summary

该研究提出了一种基于多尺度2D高斯点阵和轻量变形网络的实时视频压缩框架，解决了超高清视频高效存储与解码延迟问题。

Abstract

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.

Problem

• Ultra-High-Definition (UHD) Video
• Efficient Storage
• Real-Time Decoding
• Gaussian Splatting
• Video Compression

Innovation

• Gaussian Splatting
• Video Compression
• Deformation Network
• Rate-Distortion Performance