# GaussianSR: High Fidelity 2D Gaussian Splatting for Arbitrary-Scale Image Super-Resolution

arXiv: https://arxiv.org/abs/2407.18046 · HTML: https://mlsanity.com/paper/2407.18046/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 53 references that are in the map.
- First posted on arXiv 25 Jul 2024.

## Builds on (most cited first, 2 of 2)

- [4D Gaussian Splatting for Real-Time Dynamic Scene Rendering](https://mlsanity.com/paper/2310.08528/) (2023)
- [SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes](https://mlsanity.com/paper/2312.14937/) (2023)

## Built on by (most cited first, 30 of 32)

- [Pixel to Gaussian: Ultra-Fast Continuous Super-Resolution with 2D Gaussian Modeling](https://mlsanity.com/paper/2503.06617/) (2025)
- [Generalized and Efficient 2D Gaussian Splatting for Arbitrary-scale Super-Resolution](https://mlsanity.com/paper/2501.06838/) (2025)
- [Instant GaussianImage: A Generalizable and Self-Adaptive Image Representation via 2D Gaussian Splatting](https://mlsanity.com/paper/2506.23479/) (2025)
- [MRI Super-Resolution with Deep Learning: A Comprehensive Survey](https://mlsanity.com/paper/2511.16854/) (2025)
- [LL-GaussianImage: Efficient Image Representation for Zero-shot Low-Light Enhancement with 2D Gaussian Splatting](https://mlsanity.com/paper/2601.15772/) (2026)
- [Progressively Deformable 2D Gaussian Splatting for Video Representation at Arbitrary Resolutions](https://mlsanity.com/paper/2503.05600/) (2025)
- [Bridging Diffusion Models and 3D Representations: A 3D Consistent Super-Resolution Framework](https://mlsanity.com/paper/2508.04090/) (2025)
- [SGI: Structured 2D Gaussians for Efficient and Compact Large Image Representation](https://mlsanity.com/paper/2603.07789/) (2026)
- [Fast 2DGS: Efficient Image Representation with Deep Gaussian Prior](https://mlsanity.com/paper/2512.12774/) (2025)
- [Forecasting as Rendering: A 2D Gaussian Splatting Framework for Time Series Forecasting](https://mlsanity.com/paper/2603.02220/) (2026)
- [Lightweight Gradient-Aware Upscaling of 3D Gaussian Splatting Images](https://mlsanity.com/paper/2503.14171/) (2025)
- [GaussianVAE: Adaptive Learning Dynamics of 3D Gaussians for High-Fidelity Super-Resolution](https://mlsanity.com/paper/2506.07897/) (2025)
- [Gaussian Splatting-based Low-Rank Tensor Representation for Multi-Dimensional Image Recovery](https://mlsanity.com/paper/2511.14270/) (2025)
- [OmniScaleSR: Unleashing Scale-Controlled Diffusion Prior for Faithful and Realistic Arbitrary-Scale Image Super-Resolution](https://mlsanity.com/paper/2512.04699/) (2025)
- [Coloring the Noise: Adversarial Sobolev Alignment for Faithful Image Super Resolution](https://mlsanity.com/paper/2605.23264/) (2026)
- [Towards Arbitrary-Scale Spacecraft Image Super-Resolution via Salient Region-Guidance](https://mlsanity.com/paper/2504.18127/) (2025)
- [EMGauss: Continuous Slice-to-3D Reconstruction via Dynamic Gaussian Modeling in Volume Electron Microscopy](https://mlsanity.com/paper/2512.06684/) (2025)
- [Station2Radar: query conditioned gaussian splatting for precipitation field](https://mlsanity.com/paper/2603.00418/) (2026)
- [Voronoi-guided Bilateral 2D Gaussian Splatting for Arbitrary-Scale Hyperspectral Image Super-Resolution](https://mlsanity.com/paper/2604.17727/) (2026)
- [Flow-based Gaussian Splatting for Continuous-Scale Remote Sensing Image Super-Resolution](https://mlsanity.com/paper/2605.22147/) (2026)
- [Continuous Splatting meets Retinex: Continuous Gaussian Splatting and Implicit Reflectance Modeling for Low-Light Image Enhancement](https://mlsanity.com/paper/2606.16159/) (2026)
- [Dehaze-GaussianImage: Zero-Shot Dehazing via Efficient 2D Gaussian Splatting Representation](https://mlsanity.com/paper/2606.16163/) (2026)
- [Fi-Gaussian: Frequency-Aware Implicit Gaussian Splatting for Single Image Dehazing](https://mlsanity.com/paper/2606.16168/) (2026)
- [Gaussian Light Field Splatting: A Physical Prior-Driven Vision Transformer for Unsupervised Low-Light Image Enhancement](https://mlsanity.com/paper/2606.17985/) (2026)
- [AIGS-Net: Compact Illumination Field Modeling via 2D Gaussian Splatting for Fast Low-Light Image Enhancement](https://mlsanity.com/paper/2606.17998/) (2026)
- [Adaptive Densification for High-Fidelity and Efficient Sparse Gaussian Splatting in Arbitrary-Scale Super-Resolution](https://mlsanity.com/paper/2606.29400/) (2026)
- [Resonant Brane Splatting for Arbitrary-Scale Super-Resolution](https://mlsanity.com/paper/2606.29453/) (2026)
- [Learning Video Dynamics with Predictive Differentiable Rendering](https://mlsanity.com/paper/2606.31050/) (2026)
- [PhyMRI-SR: Toward Physics-Aware MRI Image Super-Resolution](https://mlsanity.com/paper/2607.06238/) (2026)
- [Tissue-Mixture Entropy-Weighted Reconstruction for Partial-Volume-Aware Brain MRI Super-Resolution](https://mlsanity.com/paper/2608.26647/) (2026)

## Abstract (arXiv)

Implicit neural representations (INRs) have significantly advanced the field of arbitrary-scale super-resolution (ASSR) of images. Most existing INR-based ASSR networks first extract features from the given low-resolution image using an encoder, and then render the super-resolved result via a multi-layer perceptron decoder. Although these approaches have shown promising results, their performance is constrained by the limited representation ability of discrete latent codes in the encoded features. In this paper, we propose a novel ASSR method named GaussianSR that overcomes this limitation through 2D Gaussian Splatting (2DGS). Unlike traditional methods that treat pixels as discrete points, GaussianSR represents each pixel as a continuous Gaussian field. The encoded features are simultaneously refined and upsampled by rendering the mutually stacked Gaussian fields. As a result, long-range dependencies are established to enhance representation ability. In addition, a classifier is developed to dynamically assign Gaussian kernels to all pixels to further improve flexibility. All components of GaussianSR (i.e., encoder, classifier, Gaussian kernels, and decoder) are jointly learned end-to-end. Experiments demonstrate that GaussianSR achieves superior ASSR performance with fewer parameters than existing methods while enjoying interpretable and content-aware feature aggregations.