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.
View on arXiv@article{zhang2025_2407.01866,
title={ Image-GS: Content-Adaptive Image Representation via 2D Gaussians },
author={ Yunxiang Zhang and Bingxuan Li and Alexandr Kuznetsov and Akshay Jindal and Stavros Diolatzis and Kenneth Chen and Anton Sochenov and Anton Kaplanyan and Qi Sun },
journal={arXiv preprint arXiv:2407.01866},
year={ 2025 }
}