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

arXiv: https://arxiv.org/abs/2407.01866 · HTML: https://mlsanity.com/paper/2407.01866/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 75 references that are in the map.
- First posted on arXiv 2 Jul 2024.

## Builds on (most cited first, 30 of 39)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [Implicit Neural Representations with Periodic Activation Functions](https://mlsanity.com/paper/2006.09661/) (2020)
- [Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains](https://mlsanity.com/paper/2006.10739/) (2020)
- [2D Gaussian Splatting for Geometrically Accurate Radiance Fields](https://mlsanity.com/paper/2403.17888/) (2024)
- [Variational image compression with a scale hyperprior](https://mlsanity.com/paper/1802.01436/) (2018)
- [Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations](https://mlsanity.com/paper/1906.01618/) (2019)
- [Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis](https://mlsanity.com/paper/2308.09713/) (2023)
- [Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervision](https://mlsanity.com/paper/1912.07372/) (2019)
- [End-to-end Optimized Image Compression](https://mlsanity.com/paper/1611.01704/) (2016)
- [Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules](https://mlsanity.com/paper/2001.01568/) (2020)
- [Learning Continuous Image Representation with Local Implicit Image Function](https://mlsanity.com/paper/2012.09161/) (2020)
- [Lossy Image Compression with Compressive Autoencoders](https://mlsanity.com/paper/1703.00395/) (2017)
- [Differentiable Surface Splatting for Point-based Geometry Processing](https://mlsanity.com/paper/1906.04173/) (2019)
- [COIN: COmpression with Implicit Neural representations](https://mlsanity.com/paper/2103.03123/) (2021)
- [WIRE: Wavelet Implicit Neural Representations](https://mlsanity.com/paper/2301.05187/) (2023)
- [Point-Based Neural Rendering with Per-View Optimization](https://mlsanity.com/paper/2109.02369/) (2021)
- [3DGStream: On-the-Fly Training of 3D Gaussians for Efficient Streaming of Photo-Realistic Free-Viewpoint Videos](https://mlsanity.com/paper/2403.01444/) (2024)
- [State of the Art on Diffusion Models for Visual Computing](https://mlsanity.com/paper/2310.07204/) (2023)
- [Variable Bitrate Neural Fields](https://mlsanity.com/paper/2206.07707/) (2022)
- [GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian Splatting](https://mlsanity.com/paper/2403.08551/) (2024)
- [Art and the science of generative AI: A deeper dive](https://mlsanity.com/paper/2306.04141/) (2023)
- [ReLU Fields: The Little Non-linearity That Could](https://mlsanity.com/paper/2205.10824/) (2022)
- [Neural Point Catacaustics for Novel-View Synthesis of Reflections](https://mlsanity.com/paper/2301.01087/) (2023)
- [ACORN: Adaptive Coordinate Networks for Neural Scene Representation](https://mlsanity.com/paper/2105.02788/) (2021)

## Built on by (most cited first, 30 of 35)

- [Instant GaussianImage: A Generalizable and Self-Adaptive Image Representation via 2D Gaussian Splatting](https://mlsanity.com/paper/2506.23479/) (2025)
- [HybridGS: Decoupling Transients and Statics with 2D and 3D Gaussian Splatting](https://mlsanity.com/paper/2412.03844/) (2024)
- [GSVC: Efficient Video Representation and Compression Through 2D Gaussian Splatting](https://mlsanity.com/paper/2501.12060/) (2025)
- [Upsample Anything: A Simple and Hard to Beat Baseline for Feature Upsampling](https://mlsanity.com/paper/2511.16301/) (2025)
- [Bezier Splatting for Fast and Differentiable Vector Graphics Rendering](https://mlsanity.com/paper/2503.16424/) (2025)
- [Fast and Explicit: Slice-to-Volume Reconstruction via 3D Gaussian Primitives with Analytic Point Spread Function Modeling](https://mlsanity.com/paper/2512.11624/) (2025)
- [SASNet: Spatially-Adaptive Sinusoidal Networks for INRs](https://mlsanity.com/paper/2503.09750/) (2025)
- [SGI: Structured 2D Gaussians for Efficient and Compact Large Image Representation](https://mlsanity.com/paper/2603.07789/) (2026)
- [GSVR: 2D Gaussian-based Video Representation for 800+ FPS with Hybrid Deformation Field](https://mlsanity.com/paper/2507.05594/) (2025)
- [EGGS: Exchangeable 2D/3D Gaussian Splatting for Geometry-Appearance Balanced Novel View Synthesis](https://mlsanity.com/paper/2512.02932/) (2025)
- [Fast 2DGS: Efficient Image Representation with Deep Gaussian Prior](https://mlsanity.com/paper/2512.12774/) (2025)
- [Contour Information Aware 2D Gaussian Splatting for Image Representation](https://mlsanity.com/paper/2512.23255/) (2025)
- [Versatile Video Representation via Feed-Forward 2D Gaussian Splatting Tokenization](https://mlsanity.com/paper/2508.11183/) (2025)
- [2D Gaussians Meet Visual Tokenizer](https://mlsanity.com/paper/2508.13515/) (2025)
- [NISF++: Geometrically-grounded implicit representations of 3D+time cardiac function from 2D short- and long-axis MR views](https://mlsanity.com/paper/2608.00752/) (2026)
- [Heat Kernel Textures: the Geodesic Gaussians That Do Not Splat](https://mlsanity.com/paper/2609.07557/) (2026)
- [Complex-Valued 2D Gaussian Representation for Computer-Generated Holography](https://mlsanity.com/paper/2511.15022/) (2025)
- [SmartSplat: Feature-Smart Gaussians for Scalable Compression of Ultra-High-Resolution Images](https://mlsanity.com/paper/2512.20377/) (2025)
- [ProxyImg: Towards Highly-Controllable Image Representation via Hierarchical Disentangled Proxy Embedding](https://mlsanity.com/paper/2602.01881/) (2026)
- [Station2Radar: query conditioned gaussian splatting for precipitation field](https://mlsanity.com/paper/2603.00418/) (2026)
- [Generative 3D Gaussian Splatting for Arbitrary-ResolutionAtmospheric Downscaling and Forecasting](https://mlsanity.com/paper/2604.07928/) (2026)
- [Soft Anisotropic Diagrams for Differentiable Image Representation](https://mlsanity.com/paper/2604.21984/) (2026)
- [Faster 3D Gaussian Splatting Convergence via Structure-Aware Densification](https://mlsanity.com/paper/2604.28016/) (2026)
- [Vector Scaffolding: Inter-Scale Orchestration for Differentiable Image Vectorization](https://mlsanity.com/paper/2605.11913/) (2026)
- [GLUT: 3D Gaussian Lookup Table for Continuous Color Transformation](https://mlsanity.com/paper/2605.19889/) (2026)
- [AIR: Amortized Image Reconstruction Framework for Self-Supervised Feed-Forward 2D Gaussian Splatting](https://mlsanity.com/paper/2605.20820/) (2026)
- [Neural Texture Compression using Hypernetworks](https://mlsanity.com/paper/2606.26913/) (2026)
- [Clustered Codebook Quantization for 2D Gaussian-based Image Compression](https://mlsanity.com/paper/2607.05667/) (2026)
- [HyperGS: Fast and Generalizable Gaussian Video Representation](https://mlsanity.com/paper/2607.11500/) (2026)
- [Implicit representations are dead. Long live explicit primitives!](https://mlsanity.com/paper/2608.10001/) (2026)

## Abstract (arXiv)

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.