Imaging at the quantum limit with convolutional neural networks
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913895882424320 |
|---|---|
| author | Proppe, Andrew H. Goldberg, Aaron Z. Thekkadath, Guillaume Lupu-Gladstein, Noah Jordan, Kyle M. Bustard, Philip J. Bouchard, Frédéric England, Duncan Heshami, Khabat Lundeen, Jeff S. Sussman, Benjamin J. |
| author_facet | Proppe, Andrew H. Goldberg, Aaron Z. Thekkadath, Guillaume Lupu-Gladstein, Noah Jordan, Kyle M. Bustard, Philip J. Bouchard, Frédéric England, Duncan Heshami, Khabat Lundeen, Jeff S. Sussman, Benjamin J. |
| contents | Deep neural networks have been shown to achieve exceptional performance for computer vision tasks like image recognition, segmentation, and reconstruction or denoising. Here, we evaluate the ultimate performance limits of deep convolutional neural network models for image reconstruction, by comparing them against the standard quantum limit set by shot-noise and the Heisenberg limit on precision. We train U-Net models on images of natural objects illuminated with coherent states of light, and find that the average mean-squared error of the reconstructions can surpass the standard quantum limit, and in some cases reaches the Heisenberg limit. Further, we train models on well-parameterized images for which we can calculate the quantum Cramér-Rao bound to determine the minimum possible measurable variance of an estimated parameter for a given probe state. We find the mean-squared error of the model predictions reaches these bounds calculated for the parameters, across a variety of parameterized images. These results suggest that deep convolutional neural networks can learn to become the optimal estimators allowed by the laws of physics, performing parameter estimation and image reconstruction at the ultimate possible limits of precision for the case of classical illumination of the object. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_13488 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Imaging at the quantum limit with convolutional neural networks Proppe, Andrew H. Goldberg, Aaron Z. Thekkadath, Guillaume Lupu-Gladstein, Noah Jordan, Kyle M. Bustard, Philip J. Bouchard, Frédéric England, Duncan Heshami, Khabat Lundeen, Jeff S. Sussman, Benjamin J. Machine Learning Optics Quantum Physics Deep neural networks have been shown to achieve exceptional performance for computer vision tasks like image recognition, segmentation, and reconstruction or denoising. Here, we evaluate the ultimate performance limits of deep convolutional neural network models for image reconstruction, by comparing them against the standard quantum limit set by shot-noise and the Heisenberg limit on precision. We train U-Net models on images of natural objects illuminated with coherent states of light, and find that the average mean-squared error of the reconstructions can surpass the standard quantum limit, and in some cases reaches the Heisenberg limit. Further, we train models on well-parameterized images for which we can calculate the quantum Cramér-Rao bound to determine the minimum possible measurable variance of an estimated parameter for a given probe state. We find the mean-squared error of the model predictions reaches these bounds calculated for the parameters, across a variety of parameterized images. These results suggest that deep convolutional neural networks can learn to become the optimal estimators allowed by the laws of physics, performing parameter estimation and image reconstruction at the ultimate possible limits of precision for the case of classical illumination of the object. |
| title | Imaging at the quantum limit with convolutional neural networks |
| topic | Machine Learning Optics Quantum Physics |
| url | https://arxiv.org/abs/2506.13488 |