mlsanityData to 14 Oct 2026

Pixel to Gaussian: Ultra-Fast Continuous Super-Resolution with 2D Gaussian Modeling

arXiv 2503.06617 ↗First posted 9 Mar 2025cs.CVcited by 48

Not on the map. Why?

Abstract (arXiv)

Arbitrary-scale super-resolution (ASSR) aims to reconstruct high-resolution (HR) images from low-resolution (LR) inputs with arbitrary upsampling factors using a single model, addressing the limitations of traditional SR methods constrained to fixed-scale factors (textite.g., × 2). Recent advances leveraging implicit neural representation (INR) have achieved great progress by modeling coordinate-to-pixel mappings. However, the efficiency of these methods may suffer from repeated upsampling and decoding, while their reconstruction fidelity and quality are constrained by the intrinsic representational limitations of coordinate-based functions. To address these challenges, we propose a novel ContinuousSR framework with a Pixel-to-Gaussian paradigm, which explicitly reconstructs 2D continuous HR signals from LR images using Gaussian Splatting. This approach eliminates the need for time-consuming upsampling and decoding, enabling extremely fast arbitrary-scale super-resolution. Once the Gaussian field is built in a single pass, ContinuousSR can perform arbitrary-scale rendering in just 1ms per scale. Our method introduces several key innovations. Through statistical ana

Key facts. Cited by 48 papers in the map (data through 14 Oct 2026). Builds on 47 of its 78 references that are in the map. First posted on arXiv 9 Mar 2025.

Builds on

47 of 78 references.

References · 47

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  3. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,908
  4. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,887
  5. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,552
  6. 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,264
  7. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,254
  8. 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,076
  9. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 970
  10. 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 903
  11. 2020Image Quality Assessment: Unifying Structure and Texture Similaritycited by 811
  12. 2020Learning Continuous Image Representation with Local Implicit Image Functioncited by 552
35 more
  1. 2020Plug-and-Play Image Restoration with Deep Denoiser Priorcited by 470
  2. 2019Deep Learning for Image Super-resolution: A Surveycited by 369
  3. 2016Deep Joint Rain Detection and Removal from a Single Imagecited by 352
  4. 2015Sketch-based Manga Retrieval using Manga109 Datasetcited by 329
  5. 2024A Survey on 3D Gaussian Splattingcited by 224
  6. 2023Learning A Sparse Transformer Network for Effective Image Derainingcited by 205
  7. 2019Meta-SR: A Magnification-Arbitrary Network for Super-Resolutioncited by 181
  8. 2021Local Texture Estimator for Implicit Representation Functioncited by 127
  9. 20243D Gaussian as a New Era: A Surveycited by 104
  10. 2024GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian Splattingcited by 99
  11. 2021Blind Image Super-Resolution: A Survey and Beyondcited by 93
  12. 2022CiaoSR: Continuous Implicit Attention-in-Attention Network for Arbitrary-Scale Image Super-Resolutioncited by 70
  13. 2023HAT: Hybrid Attention Transformer for Image Restorationcited by 66
  14. 2021Structure-Preserving Deraining with Residue Channel Prior Guidancecited by 63
  15. 2021UltraSR: Spatial Encoding is a Missing Key for Implicit Image Function-based Arbitrary-Scale Super-Resolutioncited by 57
  16. 2024The Ninth NTIRE 2024 Efficient Super-Resolution Challenge Reportcited by 57
  17. 2024Towards Realistic Data Generation for Real-World Super-Resolutioncited by 56
  18. 2023Cascaded Local Implicit Transformer for Arbitrary-Scale Super-Resolutioncited by 52
  19. 2023Super-Resolution Neural Operatorcited by 49
  20. 2021Implicit Transformer Network for Screen Content Image Continuous Super-Resolutioncited by 46
  21. 2024Lightweight Adaptive Feature De-drifting for Compressed Image Classificationcited by 46
  22. 2024Efficient Real-world Image Super-Resolution Via Adaptive Directional Gradient Convolutioncited by 37
  23. 2016CAS-CNN: A Deep Convolutional Neural Network for Image Compression Artifact Suppressioncited by 33
  24. 2024GaussianSR: High Fidelity 2D Gaussian Splatting for Arbitrary-Scale Image Super-Resolutioncited by 32
  25. 2025Directing Mamba to Complex Textures: An Efficient Texture-Aware State Space Model for Image Restorationcited by 28
  26. 2024QMambaBSR: Burst Image Super-Resolution with Query State Space Modelcited by 27
  27. 2024Unveiling Hidden Details: A RAW Data-Enhanced Paradigm for Real-World Super-Resolutioncited by 26
  28. 2024Latent Modulated Function for Computational Optimal Continuous Image Representationcited by 21
  29. 2025Generalized and Efficient 2D Gaussian Splatting for Arbitrary-scale Super-Resolutioncited by 21
  30. 2021Efficient and Accurate Multi-scale Topological Network for Single Image Dehazingcited by 14
  31. 2024S3Mamba: Arbitrary-Scale Super-Resolution via Scaleable State Space Modelcited by 12
  32. 2024Arbitrary-Scale Video Super-Resolution with Structural and Textural Priorscited by 9
  33. 2025GaussianToken: An Effective Image Tokenizer with 2D Gaussian Splattingcited by 9
  34. 2023How to Fine-tune the Model: Unified Model Shift and Model Bias Policy Optimizationcited by 6
  35. 2024Local Implicit Wavelet Transformer for Arbitrary-Scale Super-Resolutioncited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 21; 2026: 27.

48 papers.

Sort:

By area:

  1. 2025Enhance Then Search: An Augmentation-Search Strategy with Foundation Models for Cross-Domain Few-Shot Object Detectioncited by 24
  2. 2025SCALAR: Scale-wise Controllable Visual Autoregressive Learningcited by 18
  3. 2025PMQ-VE: Progressive Multi-Frame Quantization for Video Enhancementcited by 17
  4. 2026LUVE : Latent-Cascaded Ultra-High-Resolution Video Generation with Dual Frequency Expertscited by 15
  5. 2025Turbo2K: Towards Ultra-Efficient and High-Quality 2K Video Synthesiscited by 13
  6. 2025RobustGS: Unified Boosting of Feedforward 3D Gaussian Splatting under Low-Quality Conditionscited by 13
  7. 2025Dual-domain Modulation Network for Lightweight Image Super-Resolutioncited by 8
  8. 2025Eevee: Towards Close-up High-resolution Video-based Virtual Try-oncited by 7
  9. 2026LL-GaussianImage: Efficient Image Representation for Zero-shot Low-Light Enhancement with 2D Gaussian Splattingcited by 6
  10. 2025GaussianImage++: Boosted Image Representation and Compression with 2D Gaussian Splattingcited by 5
  11. 2026Depth-Synergized Mamba Meets Memory Experts for All-Day Image Reflection Separationcited by 5
  12. 2025Enhancing Zero-Shot Brain Tumor Subtype Classification via Fine-Grained Patch-Text Alignmentcited by 4
36 more
  1. 20252D Gaussian Splatting with Semantic Alignment for Image Inpaintingcited by 4
  2. 2026GDPO-SR: Group Direct Preference Optimization for One-Step Generative Image Super-Resolutioncited by 4
  3. 2025DPMambaIR: All-in-One Image Restoration via Degradation-Aware Prompt State Space Modelcited by 3
  4. 2025Diffusion-Based Image Editing: An Unforeseen Adversary to Robust Invisible Watermarkscited by 3
  5. 2026SGI: Structured 2D Gaussians for Efficient and Compact Large Image Representationcited by 3
  6. 2025SSCM: A Spatial-Semantic Consistent Model for Multi-Contrast MRI Super-Resolutioncited by 2
  7. 2026STGV: Spatio-Temporal Hash Encoding for Gaussian-based Video Representationcited by 2
  8. 2026Event-Illumination Collaborative Low-light Image Enhancement with a High-resolution Real-world Datasetcited by 2
  9. 2025Focus Through Motion: RGB-Event Collaborative Token Sparsification for Efficient Object Detectioncited by 1
  10. 2025Transformer-Progressive Mamba Network for Lightweight Image Super-Resolutioncited by 1
  11. 2025Gaussian Splatting-based Low-Rank Tensor Representation for Multi-Dimensional Image Recoverycited by 1
  12. 2026Editing on the Generative Manifold: A Theoretical and Empirical Study of General Diffusion-Based Image Editing Trade-offscited by 1
  13. 2026GS-STVSR: Ultra-Efficient Continuous Spatio-Temporal Video Super-Resolution via 2D Gaussian Splattingcited by 1
  14. 2026GarmentZoom: Generating Zoomable Images from Garment Listingscited by 1
  15. 2025FADE: Adversarial Concept Erasure in Flow Modelscited by 0
  16. 2025SemaMIL: Semantic-Aware Multiple Instance Learning with Retrieval-Guided State Space Modeling for Whole Slide Imagescited by 0
  17. 2025Robust Concept Erasure in Diffusion Models: A Theoretical Perspective on Security and Robustnesscited by 0
  18. 2025DeRainMamba: A Frequency-Aware State Space Model with Detail Enhancement for Image Derainingcited by 0
  19. 2025BasicAVSR: Arbitrary-Scale Video Super-Resolution via Image Priors and Enhanced Motion Compensationcited by 0
  20. 2026MarkCleaner: High-Fidelity Watermark Removal via Imperceptible Micro-Geometric Perturbationcited by 0
  21. 2026ProxyImg: Towards Highly-Controllable Image Representation via Hierarchical Disentangled Proxy Embeddingcited by 0
  22. 2026Station2Radar: query conditioned gaussian splatting for precipitation fieldcited by 0
  23. 2026When Denoising Becomes Unsigning: Theoretical and Empirical Analysis of Watermark Fragility Under Diffusion-Based Image Editingcited by 0
  24. 2026Editing Away the Evidence: Diffusion-Based Image Manipulation and the Failure Modes of Robust Watermarkingcited by 0
  25. 2026ReconMIL: Synergizing Latent Space Reconstruction with Bi-Stream Mamba for Whole Slide Image Analysiscited by 0
  26. 2026Voronoi-guided Bilateral 2D Gaussian Splatting for Arbitrary-Scale Hyperspectral Image Super-Resolutioncited by 0
  27. 2026GSPan: A Continuous Gaussian Primitive Representation for Arbitrary-Scale Pansharpeningcited by 0
  28. 2026Adaptive Densification for High-Fidelity and Efficient Sparse Gaussian Splatting in Arbitrary-Scale Super-Resolutioncited by 0
  29. 2026Resonant Brane Splatting for Arbitrary-Scale Super-Resolutioncited by 0
  30. 2026Learning Video Dynamics with Predictive Differentiable Renderingcited by 0
  31. 2026PhyMRI-SR: Toward Physics-Aware MRI Image Super-Resolutioncited by 0
  32. 2026MicroZoom: Structure-Preserving Detail Synthesis at Extreme Scalecited by 0
  33. 2026PhoenixSR: Generative Heterogeneous Distillation Unleashes Efficient Models for Real-World Super-Resolutioncited by 0
  34. 2026FoundDSR: A Generalizable Foundation Model with Guided 2D Gaussian Splatting for Depth Super-Resolutioncited by 0
  35. 2026Super-Resolving Unseen Hyperspectral Sensors at Any Scale via Spatial Operatorscited by 0
  36. 2026Gaussian Density Splatting Networkcited by 0