Self-Supervised Spatially Variant PSF Estimation for Aberration-Aware Depth-from-Defocus
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929258471882752 |
|---|---|
| author | Wu, Zhuofeng Monno, Yusuke Okutomi, Masatoshi |
| author_facet | Wu, Zhuofeng Monno, Yusuke Okutomi, Masatoshi |
| contents | In this paper, we address the task of aberration-aware depth-from-defocus (DfD), which takes account of spatially variant point spread functions (PSFs) of a real camera. To effectively obtain the spatially variant PSFs of a real camera without requiring any ground-truth PSFs, we propose a novel self-supervised learning method that leverages the pair of real sharp and blurred images, which can be easily captured by changing the aperture setting of the camera. In our PSF estimation, we assume rotationally symmetric PSFs and introduce the polar coordinate system to more accurately learn the PSF estimation network. We also handle the focus breathing phenomenon that occurs in real DfD situations. Experimental results on synthetic and real data demonstrate the effectiveness of our method regarding both the PSF estimation and the depth estimation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_18175 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Self-Supervised Spatially Variant PSF Estimation for Aberration-Aware Depth-from-Defocus Wu, Zhuofeng Monno, Yusuke Okutomi, Masatoshi Computer Vision and Pattern Recognition Image and Video Processing In this paper, we address the task of aberration-aware depth-from-defocus (DfD), which takes account of spatially variant point spread functions (PSFs) of a real camera. To effectively obtain the spatially variant PSFs of a real camera without requiring any ground-truth PSFs, we propose a novel self-supervised learning method that leverages the pair of real sharp and blurred images, which can be easily captured by changing the aperture setting of the camera. In our PSF estimation, we assume rotationally symmetric PSFs and introduce the polar coordinate system to more accurately learn the PSF estimation network. We also handle the focus breathing phenomenon that occurs in real DfD situations. Experimental results on synthetic and real data demonstrate the effectiveness of our method regarding both the PSF estimation and the depth estimation. |
| title | Self-Supervised Spatially Variant PSF Estimation for Aberration-Aware Depth-from-Defocus |
| topic | Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2402.18175 |