mlsanityData to 7 Oct 2026

SinDiffusion: Learning a Diffusion Model from a Single Natural Image

arXiv 2211.12445 ↗First posted 22 Nov 2022cs.CVcited by 42

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

We present SinDiffusion, leveraging denoising diffusion models to capture internal distribution of patches from a single natural image. SinDiffusion significantly improves the quality and diversity of generated samples compared with existing GAN-based approaches. It is based on two core designs. First, SinDiffusion is trained with a single model at a single scale instead of multiple models with progressive growing of scales which serves as the default setting in prior work. This avoids the accumulation of errors, which cause characteristic artifacts in generated results. Second, we identify that a patch-level receptive field of the diffusion network is crucial and effective for capturing the image's patch statistics, therefore we redesign the network structure of the diffusion model. Coupling these two designs enables us to generate photorealistic and diverse images from a single image. Furthermore, SinDiffusion can be applied to various applications, i.e., text-guided image generation, and image outpainting, due to the inherent capability of diffusion models. Extensive experiments on a wide range of images demonstrate the superiority of our proposed method for modeling the patch distribution.

Key facts. Cited by 42 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 46 of its 66 references that are in the map. First posted on arXiv 22 Nov 2022.

Builds on

46 of 66 references.

Closest ancestors · 15

Same direction, newest first

  1. 2022Classifier-Free Diffusion Guidance26 Jul
  2. 2022EGSDE: Unpaired Image-to-Image Translation via Energy-Guided Stochastic Differential Equations14 Jul
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  4. 2021Vector Quantized Diffusion Model for Text-to-Image Synthesis29 Nov
  5. 2021ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models6 Aug
  6. 2021Structured Denoising Diffusion Models in Discrete State-Spaces7 Jul
  7. 2021Variational Diffusion Models1 Jul
  8. 2021On Fast Sampling of Diffusion Probabilistic Models31 May
  9. 2021Cascaded Diffusion Models for High Fidelity Image Generation30 May
  10. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  11. 2021UNIT-DDPM: UNpaired Image Translation with Denoising Diffusion Probabilistic Models12 Apr
  12. 2021Noise Estimation for Generative Diffusion Models6 Apr
3 more
  1. 2021Improved Denoising Diffusion Probabilistic Models18 Feb
  2. 2020Denoising Diffusion Implicit Models6 Oct
  3. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 31

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  4. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  5. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
  6. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,409
  7. 2021Image Super-Resolution via Iterative Refinementcited by 1,506
  8. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,419
  9. 2021Palette: Image-to-Image Diffusion Modelscited by 1,296
  10. 2021StyleCLIP: Text-Driven Manipulation of StyleGAN Imagerycited by 990
  11. 2022Denoising Diffusion Restoration Modelscited by 951
  12. 2021Blended Diffusion for Text-driven Editing of Natural Imagescited by 924
19 more
  1. 2018Free-Form Image Inpainting with Gated Convolutioncited by 594
  2. 2017Understanding the Effective Receptive Field in Deep Convolutional Neural Networkscited by 549
  3. 2021SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Modelscited by 415
  4. 2019SinGAN: Learning a Generative Model from a Single Natural Imagecited by 348
  5. 2022Dual Diffusion Implicit Bridges for Image-to-Image Translationcited by 212
  6. 2019ManiGAN: Text-Guided Image Manipulationcited by 156
  7. 2020Improved Techniques for Training Single-Image GANscited by 77
  8. 2019A critical analysis of self-supervision, or what we can learn from a single imagecited by 75
  9. 2019Boundless: Generative Adversarial Networks for Image Extensioncited by 62
  10. 2021InfinityGAN: Towards Infinite-Pixel Image Synthesiscited by 61
  11. 2021Drop the GAN: In Defense of Patches Nearest Neighbors as Single Image Generative Modelscited by 51
  12. 2021StyleMC: Multi-Channel Based Fast Text-Guided Image Generation and Manipulationcited by 40
  13. 2020TuiGAN: Learning Versatile Image-to-Image Translation with Two Unpaired Imagescited by 23
  14. 2020PFA-GAN: Progressive Face Aging with Generative Adversarial Networkcited by 19
  15. 2022PetsGAN: Rethinking Priors for Single Image Generationcited by 14
  16. 2021SinIR: Efficient General Image Manipulation with Single Image Reconstructioncited by 13
  17. 2021ExSinGAN: Learning an Explainable Generative Model from a Single Imagecited by 12
  18. 2021MOGAN: Morphologic-structure-aware Generative Learning from a Single Imagecited by 9
  19. 2021Generating Novel Scene Compositions from Single Images and Videoscited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 22; 2024: 5; 2025: 9; 2026: 4.

42 papers.

Sort:

By area:

  1. 2023Text-to-image Diffusion Models in Generative AI: A Surveycited by 264
  2. 2023Implicit Diffusion Models for Continuous Super-Resolutioncited by 216
  3. 2023Patch Diffusion: Faster and More Data-Efficient Training of Diffusion Modelscited by 131
  4. 2023Single Motion Diffusioncited by 65
  5. 2022SinDDM: A Single Image Denoising Diffusion Modelcited by 60
  6. 2023Designing a Better Asymmetric VQGAN for StableDiffusioncited by 45
  7. 2024Towards a Mechanistic Explanation of Diffusion Model Generalizationcited by 42
  8. 2023DDS2M: Self-Supervised Denoising Diffusion Spatio-Spectral Model for Hyperspectral Image Restorationcited by 32
  9. 2023Controllable Mind Visual Diffusion Modelcited by 29
  10. 2023Sin3DM: Learning a Diffusion Model from a Single 3D Textured Shapecited by 29
  11. 2023DiffInfinite: Large Mask-Image Synthesis via Parallel Random Patch Diffusion in Histopathologycited by 28
  12. 2024Hierarchical Patch Diffusion Models for High-Resolution Video Generationcited by 24
30 more
  1. 2023Rethinking Exemplars for Continual Semantic Segmentation in Endoscopy Scenes: Entropy-based Mini-Batch Pseudo-Replaycited by 20
  2. 2023A Survey on Generative Modeling with Limited Data, Few Shots, and Zero Shotcited by 19
  3. 2024Continuous-Multiple Image Outpainting in One-Step via Positional Query and A Diffusion-based Approachcited by 18
  4. 2025Does Generation Require Memorization? Creative Diffusion Models using Ambient Diffusioncited by 17
  5. 2023Defect Spectrum: A Granular Look of Large-Scale Defect Datasets with Rich Semanticscited by 16
  6. 2022Seeing a Rose in Five Thousand Wayscited by 13
  7. 2023STDiff: Spatio-temporal Diffusion for Continuous Stochastic Video Predictioncited by 12
  8. 2023IPDreamer: Appearance-Controllable 3D Object Generation with Complex Image Promptscited by 11
  9. 2023Single Mesh Diffusion Models with Field Latents for Texture Generationcited by 11
  10. 2023Image Synthesis under Limited Data: A Survey and Taxonomycited by 9
  11. 2025LightsOut: Diffusion-based Outpainting for Enhanced Lens Flare Removalcited by 9
  12. 2023Towards Real-time Text-driven Image Manipulation with Unconditional Diffusion Modelscited by 7
  13. 2023DDRF: Denoising Diffusion Model for Remote Sensing Image Fusioncited by 6
  14. 2023The Missing U for Efficient Diffusion Modelscited by 5
  15. 2023GRIG: Few-Shot Generative Residual Image Inpaintingcited by 4
  16. 2024Latent Representation Matters: Human-like Sketches in One-shot Drawing Taskscited by 3
  17. 2025TriTex: Learning Texture from a Single Mesh via Triplane Semantic Featurescited by 2
  18. 2023TcGAN: Semantic-Aware and Structure-Preserved GANs with Individual Vision Transformer for Fast Arbitrary One-Shot Image Generationcited by 1
  19. 2025Example-Based Feature Painting on Texturescited by 1
  20. 2025DreamOmni3: Scribble-based Editing and Generationcited by 1
  21. 2026StructDiff: A Structure-Preserving and Spatially Controllable Diffusion Model for Single-Image Generationcited by 1
  22. 2026Efficient and Training-Free Single-Image Diffusion Modelscited by 1
  23. 2023SVDM: Single-View Diffusion Model for Pseudo-Stereo 3D Object Detectioncited by 0
  24. 2024ExCellGen: Fast, Controllable, Photorealistic 3D Scene Generation from a Single Real-World Exemplarcited by 0
  25. 2025KernelFusion: Assumption-Free Blind Super-Resolution via Patch Diffusioncited by 0
  26. 2025HALO: Human-Aligned End-to-end Image Retargeting with Layered Transformationscited by 0
  27. 2025Reimagining Parameter Space Exploration with Diffusion Modelscited by 0
  28. 2025SinSEMI: A One-Shot Image Generation Model and Data-Efficient Evaluation Framework for Semiconductor Inspection Equipmentcited by 0
  29. 2026Bottom-up Modeling of Repeated Elements via Single Image Analysis-by-Synthesiscited by 0
  30. 2026FRPSS: Feature Rearrangement in Pre-Shape Space for Single-Image Generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023DiffGANPaint: Fast Inpainting Using Denoising Diffusion GANs
  2. 2024Latent Denoising Diffusion GAN: Faster sampling, Higher image quality
  3. 2025Revisiting Diffusion Models: From Generative Pre-training to One-Step Generation
  4. 2022SinFusion: Training Diffusion Models on a Single Image or Video
  5. 2023Patched Denoising Diffusion Models For High-Resolution Image Synthesis
  6. 2024Diffusion Models in Low-Level Vision: A Survey
  7. 2022Wavelet Diffusion Models are fast and scalable Image Generators
  8. 2023DiffMorpher: Unleashing the Capability of Diffusion Models for Image Morphing