mlsanityData to 14 Oct 2026

Personalized Generative Low-light Image Denoising and Enhancement

arXiv 2412.14327 ↗First posted 18 Dec 2024cs.CVcited by 1

On the map: Diffusion models → Inverse problems and image restoration

Abstract (arXiv)

Modern cameras' performance in low-light conditions remains suboptimal due to fundamental limitations in photon shot noise and sensor read noise. Generative image restoration methods have shown promising results compared to traditional approaches, but they suffer from hallucinatory content generation when the signal-to-noise ratio (SNR) is low. Leveraging the availability of personalized photo galleries of the users, we introduce Diffusion-based Personalized Generative Denoising (DiffPGD), a new approach that builds a customized diffusion model for individual users. Our key innovation lies in the development of an identity-consistent physical buffer that extracts the physical attributes of the person from the gallery. This ID-consistent physical buffer serves as a robust prior that can be seamlessly integrated into the diffusion model to restore degraded images without the need for fine-tuning. Over a wide range of low-light testing scenarios, we show that DiffPGD achieves superior image denoising and enhancement performance compared to existing diffusion-based denoising approaches. Our project page can be found at hrefhttps://genai-restore.github.io/DiffPGD/textcolorpurplehttps://genai-restore.github.io/DiffPGD/.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models. Builds on 52 of its 86 references that are in the map. First posted on arXiv 18 Dec 2024.

Builds on

52 of 86 references.

Closest ancestors · 6

Same direction, newest first

  1. 2024Overcoming False Illusions in Real-World Face Restoration with Multi-Modal Guided Diffusion Model5 Oct
  2. 2023Restoration by Generation with Constrained Priors28 Dec
  3. 2023ExposureDiffusion: Learning to Expose for Low-light Image Enhancement15 Jul
  4. 2023Low-Light Image Enhancement with Wavelet-based Diffusion Models1 Jun
  5. 2023Denoising Diffusion Models for Plug-and-Play Image Restoration15 May
  6. 2022Denoising Diffusion Restoration Models27 Jan

Other references · 46

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  5. 2020Denoising Diffusion Implicit Modelscited by 9,781
  6. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  7. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  8. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  9. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  10. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,849
  11. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,333
  12. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,887
34 more
  1. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,358
  2. 2018Demystifying MMD GANscited by 1,293
  3. 2017VGGFace2: A dataset for recognising faces across pose and agecited by 914
  4. 2018Deep Retinex Decomposition for Low-Light Enhancementcited by 723
  5. 2019MaskGAN: Towards Diverse and Interactive Facial Image Manipulationcited by 628
  6. 2021Designing an Encoder for StyleGAN Image Manipulationcited by 544
  7. 2020Zero-Reference Deep Curve Estimation for Low-Light Image Enhancementcited by 542
  8. 2020Learning an Animatable Detailed 3D Face Model from In-The-Wild Imagescited by 477
  9. 2019EnlightenGAN: Deep Light Enhancement without Paired Supervisioncited by 466
  10. 2018Learning to See in the Darkcited by 460
  11. 2016Deep Convolutional Neural Network for Inverse Problems in Imagingcited by 433
  12. 2021Towards Real-World Blind Face Restoration with Generative Facial Priorcited by 349
  13. 2020Learning Enriched Features for Real Image Restoration and Enhancementcited by 312
  14. 2022Perception Prioritized Training of Diffusion Modelscited by 303
  15. 2018Toward Convolutional Blind Denoising of Real Photographscited by 274
  16. 2018Unprocessing Images for Learned Raw Denoisingcited by 250
  17. 2022Towards Robust Blind Face Restoration with Codebook Lookup Transformercited by 231
  18. 2021FaceFormer: Speech-Driven 3D Facial Animation with Transformerscited by 209
  19. 2022Learning Enriched Features for Fast Image Restoration and Enhancementcited by 150
  20. 2020A Physics-based Noise Formation Model for Extreme Low-light Raw Denoisingcited by 138
  21. 2022RestoreFormer: High-Quality Blind Face Restoration from Undegraded Key-Value Pairscited by 85
  22. 2023DR2: Diffusion-based Robust Degradation Remover for Blind Face Restorationcited by 79
  23. 2021Adaptive Unfolding Total Variation Network for Low-Light Image Enhancementcited by 55
  24. 2022Learning Dual Memory Dictionaries for Blind Face Restorationcited by 40
  25. 2023Xformer: Hybrid X-Shaped Transformer for Image Denoisingcited by 37
  26. 2023Diffusion in the Dark: A Diffusion Model for Low-Light Text Recognitioncited by 20
  27. 2022Efficient Visual Computing with Camera RAW Snapshotscited by 18
  28. 2020Dynamic Low-light Imaging with Quanta Image Sensorscited by 16
  29. 2021Learning to Aggregate and Personalize 3D Face from In-the-Wild Photo Collectioncited by 16
  30. 2021Progressive Joint Low-light Enhancement and Noise Removal for Raw Imagescited by 16
  31. 2024PFStorer: Personalized Face Restoration and Super-Resolutioncited by 13
  32. 2018Correction by Projection: Denoising Images with Generative Adversarial Networkscited by 11
  33. 2023Real-World Denoising via Diffusion Modelcited by 10
  34. 2023Learning to See Low-Light Images via Feature Domain Adaptationcited by 8

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025ReTiDe: Real-Time Denoising for Energy-Efficient Motion Picture Processing with FPGAscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025LowDiff: Efficient Diffusion Sampling with Low-Resolution Condition
  2. 2023Generative Diffusion Prior for Unified Image Restoration and Enhancement
  3. 2023DIFFNAT: Improving Diffusion Image Quality Using Natural Image Statistics
  4. 2023PartDiff: Image Super-resolution with Partial Diffusion Models
  5. 2024Taming Diffusion Models for Image Restoration: A Review
  6. 2025A Simple Combination of Diffusion Models for Better Quality Trade-Offs in Image Denoising
  7. 2023DiffLLE: Diffusion-guided Domain Calibration for Unsupervised Low-light Image Enhancement
  8. 2025Compressed Image Generation with Denoising Diffusion Codebook Models