pith. sign in

arxiv: 2403.08551 · v5 · pith:S7GLYRJ6new · submitted 2024-03-13 · 📡 eess.IV · cs.AI· cs.CV· cs.MM

GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian Splatting

classification 📡 eess.IV cs.AIcs.CVcs.MM
keywords imagecoingaussianrepresentationcodeccompressiongaussianimageinrs
0
0 comments X
read the original abstract

Implicit neural representations (INRs) recently achieved great success in image representation and compression, offering high visual quality and fast rendering speeds with 10-1000 FPS, assuming sufficient GPU resources are available. However, this requirement often hinders their use on low-end devices with limited memory. In response, we propose a groundbreaking paradigm of image representation and compression by 2D Gaussian Splatting, named GaussianImage. We first introduce 2D Gaussian to represent the image, where each Gaussian has 8 parameters including position, covariance and color. Subsequently, we unveil a novel rendering algorithm based on accumulated summation. Remarkably, our method with a minimum of 3$\times$ lower GPU memory usage and 5$\times$ faster fitting time not only rivals INRs (e.g., WIRE, I-NGP) in representation performance, but also delivers a faster rendering speed of 1500-2000 FPS regardless of parameter size. Furthermore, we integrate existing vector quantization technique to build an image codec. Experimental results demonstrate that our codec attains rate-distortion performance comparable to compression-based INRs such as COIN and COIN++, while facilitating decoding speeds of approximately 2000 FPS. Additionally, preliminary proof of concept shows that our codec surpasses COIN and COIN++ in performance when using partial bits-back coding. Code is available at https://github.com/Xinjie-Q/GaussianImage.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.