# Fast 2DGS: Efficient Image Representation with Deep Gaussian Prior

arXiv: https://arxiv.org/abs/2512.12774 · HTML: https://mlsanity.com/paper/2512.12774/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 54 references that are in the map.
- First posted on arXiv 14 Dec 2025.

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

- [Implicit Neural Representations with Periodic Activation Functions](https://mlsanity.com/paper/2006.09661/) (2020)
- [Depth Anything 3: Recovering the Visual Space from Any Views](https://mlsanity.com/paper/2511.10647/) (2025)
- [Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2305.16322/) (2023)
- [Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise](https://mlsanity.com/paper/2208.09392/) (2022)
- [WIRE: Wavelet Implicit Neural Representations](https://mlsanity.com/paper/2301.05187/) (2023)
- [FreeU: Free Lunch in Diffusion U-Net](https://mlsanity.com/paper/2309.11497/) (2023)
- [Implicit Neural Representations for Image Compression](https://mlsanity.com/paper/2112.04267/) (2021)
- [MEMC-Net: Motion Estimation and Motion Compensation Driven Neural Network for Video Interpolation and Enhancement](https://mlsanity.com/paper/1810.08768/) (2018)
- [GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian Splatting](https://mlsanity.com/paper/2403.08551/) (2024)
- [COIN++: Neural Compression Across Modalities](https://mlsanity.com/paper/2201.12904/) (2022)
- [Discrete Cosine Transform Network for Guided Depth Map Super-Resolution](https://mlsanity.com/paper/2104.06977/) (2021)
- [Densely Residual Laplacian Super-Resolution](https://mlsanity.com/paper/1906.12021/) (2019)
- [Wild-GS: Real-Time Novel View Synthesis from Unconstrained Photo Collections](https://mlsanity.com/paper/2406.10373/) (2024)
- [SceneSplat: Gaussian Splatting-based Scene Understanding with Vision-Language Pretraining](https://mlsanity.com/paper/2503.18052/) (2025)
- [Finding Mixed Nash Equilibria of Generative Adversarial Networks](https://mlsanity.com/paper/1811.02002/) (2018)
- [Temporal FiLM: Capturing Long-Range Sequence Dependencies with Feature-Wise Modulations](https://mlsanity.com/paper/1909.06628/) (2019)
- [Image-GS: Content-Adaptive Image Representation via 2D Gaussians](https://mlsanity.com/paper/2407.01866/) (2024)
- [DISCO: Adversarial Defense with Local Implicit Functions](https://mlsanity.com/paper/2212.05630/) (2022)
- [GaussianSR: High Fidelity 2D Gaussian Splatting for Arbitrary-Scale Image Super-Resolution](https://mlsanity.com/paper/2407.18046/) (2024)
- [How Far Can We Compress Instant-NGP-Based NeRF?](https://mlsanity.com/paper/2406.04101/) (2024)
- [Large Images are Gaussians: High-Quality Large Image Representation with Levels of 2D Gaussian Splatting](https://mlsanity.com/paper/2502.09039/) (2025)
- [FreeStyle: Free Lunch for Text-guided Style Transfer using Diffusion Models](https://mlsanity.com/paper/2401.15636/) (2024)
- [RGB no more: Minimally-decoded JPEG Vision Transformers](https://mlsanity.com/paper/2211.16421/) (2022)
- [Instant GaussianImage: A Generalizable and Self-Adaptive Image Representation via 2D Gaussian Splatting](https://mlsanity.com/paper/2506.23479/) (2025)
- [HDGS: Textured 2D Gaussian Splatting for Enhanced Scene Rendering](https://mlsanity.com/paper/2412.01823/) (2024)
- [CUNSB-RFIE: Context-aware Unpaired Neural Schr"odinger Bridge in Retinal Fundus Image Enhancement](https://mlsanity.com/paper/2409.10966/) (2024)
- [MiraGe: Editable 2D Images using Gaussian Splatting](https://mlsanity.com/paper/2410.01521/) (2024)
- [A DCT Approximation for Image Compression](https://mlsanity.com/paper/1402.6034/) (2014)
- [GaussianToken: An Effective Image Tokenizer with 2D Gaussian Splatting](https://mlsanity.com/paper/2501.15619/) (2025)
- [Latent Radiance Fields with 3D-aware 2D Representations](https://mlsanity.com/paper/2502.09613/) (2025)

## Built on by (most cited first, 2 of 2)

- [Soft Anisotropic Diagrams for Differentiable Image Representation](https://mlsanity.com/paper/2604.21984/) (2026)
- [Locality-Aware Density Control for Efficient Gaussian-based Image Representation](https://mlsanity.com/paper/2607.17896/) (2026)

## Abstract (arXiv)

As generative models become increasingly capable of producing high-fidelity visual content, the demand for efficient, interpretable, and editable image representations has grown substantially. Recent advances in 2D Gaussian Splatting (2DGS) have emerged as a promising solution, offering explicit control, high interpretability, and real-time rendering capabilities (>1000 FPS). However, high-quality 2DGS typically requires post-optimization. Existing methods adopt random or heuristics (e.g., gradient maps), which are often insensitive to image complexity and lead to slow convergence (>10s). More recent approaches introduce learnable networks to predict initial Gaussian configurations, but at the cost of increased computational and architectural complexity. To bridge this gap, we present Fast-2DGS, a lightweight framework for efficient Gaussian image representation. Specifically, we introduce Deep Gaussian Prior, implemented as a conditional network to capture the spatial distribution of Gaussian primitives under different complexities. In addition, we propose an attribute regression network to predict dense Gaussian properties. Experiments demonstrate that this disentangled architecture achieves high-quality reconstruction in a single forward pass, followed by minimal fine-tuning. More importantly, our approach significantly reduces computational cost without compromising visual quality, bringing 2DGS closer to industry-ready deployment.