Image-GS: Content-Adaptive Image Representation via 2D Gaussians

TL;DR

Image-GS introduces a content-adaptive, Gaussian-based image representation that balances visual quality and memory efficiency, enabling real-time graphics applications with rapid random access and versatile compression capabilities.

Contribution

The paper presents a novel, content-adaptive image representation using 2D Gaussians, optimized with a differentiable renderer for real-time, memory-efficient image reconstruction.

Findings

Achieves high visual fidelity with low memory usage.

Supports real-time decoding with only 0.3K MACs per pixel.

Demonstrates versatility in compression and restoration tasks.

Abstract

Neural image representations have emerged as a promising approach for encoding and rendering visual data. Combined with learning-based workflows, they demonstrate impressive trade-offs between visual fidelity and memory footprint. Existing methods in this domain, however, often rely on fixed data structures that suboptimally allocate memory or compute-intensive implicit models, hindering their practicality for real-time graphics applications. Inspired by recent advancements in radiance field rendering, we introduce Image-GS, a content-adaptive image representation based on 2D Gaussians. Leveraging a custom differentiable renderer, Image-GS reconstructs images by adaptively allocating and progressively optimizing a group of anisotropic, colored 2D Gaussians. It achieves a favorable balance between visual fidelity and memory efficiency across a variety of stylized images frequently seen in graphics workflows, especially for those showing non-uniformly distributed features and in low-bitrate regimes. Moreover, it supports hardware-friendly rapid random access for real-time usage, requiring only 0.3K MACs to decode a pixel. Through error-guided progressive optimization, Image-GS naturally constructs a smooth level-of-detail hierarchy. We demonstrate its versatility with several applications, including texture compression, semantics-aware compression, and joint image compression and restoration.