Curriculum Learning for ab initio Deep Learned Refractive Optics
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914902851977216 |
|---|---|
| author | Yang, Xinge Fu, Qiang Heidrich, Wolfgang |
| author_facet | Yang, Xinge Fu, Qiang Heidrich, Wolfgang |
| contents | Deep optical optimization has recently emerged as a new paradigm for designing computational imaging systems using only the output image as the objective. However, it has been limited to either simple optical systems consisting of a single element such as a diffractive optical element (DOE) or metalens, or the fine-tuning of compound lenses from good initial designs. Here we present a DeepLens design method based on curriculum learning, which is able to learn optical designs of compound lenses ab initio from randomly initialized surfaces without human intervention, therefore overcoming the need for a good initial design. We demonstrate the effectiveness of our approach by fully automatically designing both classical imaging lenses and a large field-of-view extended depth-of-field computational lens in a cellphone-style form factor, with highly aspheric surfaces and a short back focal length. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2302_01089 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Curriculum Learning for ab initio Deep Learned Refractive Optics Yang, Xinge Fu, Qiang Heidrich, Wolfgang Computer Vision and Pattern Recognition Machine Learning Image and Video Processing Optics Deep optical optimization has recently emerged as a new paradigm for designing computational imaging systems using only the output image as the objective. However, it has been limited to either simple optical systems consisting of a single element such as a diffractive optical element (DOE) or metalens, or the fine-tuning of compound lenses from good initial designs. Here we present a DeepLens design method based on curriculum learning, which is able to learn optical designs of compound lenses ab initio from randomly initialized surfaces without human intervention, therefore overcoming the need for a good initial design. We demonstrate the effectiveness of our approach by fully automatically designing both classical imaging lenses and a large field-of-view extended depth-of-field computational lens in a cellphone-style form factor, with highly aspheric surfaces and a short back focal length. |
| title | Curriculum Learning for ab initio Deep Learned Refractive Optics |
| topic | Computer Vision and Pattern Recognition Machine Learning Image and Video Processing Optics |
| url | https://arxiv.org/abs/2302.01089 |