mlsanityData to 14 Oct 2026

All-optical image denoising using a diffractive visual processor

arXiv 2309.09215 ↗First posted 17 Sep 2023physics.optics cs.CV physics.app-phcited by 6

Not on the map. Why?

Abstract (arXiv)

Image denoising, one of the essential inverse problems, targets to remove noise/artifacts from input images. In general, digital image denoising algorithms, executed on computers, present latency due to several iterations implemented in, e.g., graphics processing units (GPUs). While deep learning-enabled methods can operate non-iteratively, they also introduce latency and impose a significant computational burden, leading to increased power consumption. Here, we introduce an analog diffractive image denoiser to all-optically and non-iteratively clean various forms of noise and artifacts from input images - implemented at the speed of light propagation within a thin diffractive visual processor. This all-optical image denoiser comprises passive transmissive layers optimized using deep learning to physically scatter the optical modes that represent various noise features, causing them to miss the output image Field-of-View (FoV) while retaining the object features of interest. Our results show that these diffractive denoisers can efficiently remove salt and pepper noise and image rendering-related spatial artifacts from input phase or intensity images while achieving an output power efficiency of ~30-40%. We experimentally demonstrated the effectiveness of this analog denoiser architecture using a 3D-printed diffractive visual processor operating at the terahertz spectrum. Owing to their speed, power-efficiency, and minimal computational overhead, all-optical diffractive denoisers can be transformative for various image display and projection systems, including, e.g., holographic displays.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 35 of its 75 references that are in the map. First posted on arXiv 17 Sep 2023.

Builds on

35 of 75 references.

References · 35

  1. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  2. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  3. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,887
  4. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,358
  5. 2021Uformer: A General U-Shaped Transformer for Image Restorationcited by 866
  6. 2017FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoisingcited by 510
  7. 2017A Neural Representation of Sketch Drawingscited by 313
  8. 2022MAXIM: Multi-Axis MLP for Image Processingcited by 302
  9. 2017Deep Bilateral Learning for Real-Time Image Enhancementcited by 200
  10. 2018All-Optical Machine Learning Using Diffractive Deep Neural Networkscited by 177
  11. 2018Neural Nearest Neighbors Networkscited by 98
  12. 2017A Review of Convolutional Neural Networks for Inverse Problems in Imagingcited by 81
23 more
  1. 2023Image Denoising: The Deep Learning Revolution and Beyond -- A Survey Paper --cited by 71
  2. 2018Predicting the Computational Cost of Deep Learning Modelscited by 49
  3. 2022GhostNetV2: Enhance Cheap Operation with Long-Range Attentioncited by 44
  4. 2020Misalignment Resilient Diffractive Optical Networkscited by 33
  5. 2019Deep Graph-Convolutional Image Denoisingcited by 32
  6. 2018Analysis of Diffractive Optical Neural Networks and Their Integration with Electronic Neural Networkscited by 30
  7. 2019Design of Task-Specific Optical Systems Using Broadband Diffractive Neural Networkscited by 27
  8. 2022Image sensing with multilayer, nonlinear optical neural networkscited by 25
  9. 2021All-Optical Synthesis of an Arbitrary Linear Transformation Using Diffractive Surfacescited by 24
  10. 2022Diffractive all-optical computing for quantitative phase imagingcited by 22
  11. 2022To image, or not to image: Class-specific diffractive cameras with all-optical erasure of undesired objectscited by 21
  12. 2021Computational Imaging Without a Computer: Seeing Through Random Diffusers at the Speed of Lightcited by 19
  13. 2023Universal Linear Intensity Transformations Using Spatially-Incoherent Diffractive Processorscited by 17
  14. 2022Snapshot Multispectral Imaging Using a Diffractive Optical Networkcited by 16
  15. 2022Data class-specific all-optical transformations and encryptioncited by 16
  16. 2020Scale-, shift- and rotation-invariant diffractive optical networkscited by 15
  17. 2022Super-resolution image display using diffractive decoderscited by 13
  18. 2022Unidirectional Imaging using Deep Learning-Designed Materialscited by 13
  19. 2022Polarization Multiplexed Diffractive Computing: All-Optical Implementation of a Group of Linear Transformations Through a Polarization-Encoded Diffractive Networkcited by 10
  20. 2023Quantitative phase imaging (QPI) through random diffusers using a diffractive optical networkcited by 10
  21. 2023Multispectral Quantitative Phase Imaging Using a Diffractive Optical Networkcited by 10
  22. 2022Massively Parallel Universal Linear Transformations using a Wavelength-Multiplexed Diffractive Optical Networkcited by 9
  23. 2023Learning Diffractive Optical Communication Around Arbitrary Opaque Occlusionscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 1; 2026: 2.

6 papers.

  1. 2024Optical Generative Modelscited by 8
  2. 2024Optical Diffusion Models for Image Generationcited by 4
  3. 2024Compute-first optical detection for noise-resilient visual perceptioncited by 0
  4. 2025Snapshot 3D image projection using a diffractive decodercited by 0
  5. 2026Pre-training Enables Extraordinary All-optical Image Denoisingcited by 0
  6. 2026Wavelength-Multiplexed 2D Beam Steering via a Passive Diffractive Networkcited by 0