Efficient compression method improves gaussian splatting video sequences
Efficient Gaussian Splatting Sequence Compression with Standard Video Codecs
Computer Vision and Pattern Recognition
Summary
Storing and sending sequences of images made with a technique called Gaussian Splatting can be tricky because the images don’t change smoothly from one frame to the next. The authors created a new way called GSCV that organizes these image frames better so standard video compressors can work more efficiently. Their method uses a step called Inter-PLAS to keep frames more alike, helping video codecs compress the sequences with better quality and smaller file sizes. Tests show their approach beats older methods using popular video and 3D point cloud compressors.
What this means in practice
- •For computer graphics engineers: Compress Gaussian Splatting image sequences more efficiently using standard video codecs in graphics workflows.
- •For 3d streaming platform developers: Improve storage and bandwidth requirements when streaming 3D scenes represented as Gaussian Splatting sequences.$Commercial implications: Enables competitive 3D streaming products with higher quality and smaller file sizes, directly enabled by GSCV compression.
Authors
Qi Yang, Shuting Xia, Le Yang, Geert Van Der Auwera, Zhu Li
Abstract
This paper presents a novel effective Gaussian Splatting (GS) sequence Compression method that utilizes the Video codec (GSCV). Existing video-based GS sequence compression relies on the Parallel Linear Assignment Sorting (PLAS) and tracked primitive information to convert GS into smooth 2D videos. However, tracked information is not available for most practical applications, and without it, using the vanilla PLAS can generate images exhibiting weak inter-frame correlation, due to its stochastic nature. GSCV incorporates a simple yet efficient Inter-PLAS method to produce close images between the I- and P-frames of GS, enhancing the inter-frame performance of video codec greatly. GSCV also realizes a new pipeline based on the state-of-the-art video codecs with high bit-depth GS images, achieving higher compressibility while simultaneously providing a higher quality upper bound. Experimental results show that the proposed GSCV exhibits obviously improved performance over MPEG video and point cloud-based anchors in GS sequence compression. The code is available at https://github.com/Qi-Yangsjtu/GSCV.