Low-Trace Adaptation of Zero-shot Self-supervised Blind Image Denoising
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929282055405568 |
|---|---|
| author | Hu, Jintong Xia, Bin Li, Bingchen Yang, Wenming |
| author_facet | Hu, Jintong Xia, Bin Li, Bingchen Yang, Wenming |
| contents | Deep learning-based denoiser has been the focus of recent development on image denoising. In the past few years, there has been increasing interest in developing self-supervised denoising networks that only require noisy images, without the need for clean ground truth for training. However, a performance gap remains between current self-supervised methods and their supervised counterparts. Additionally, these methods commonly depend on assumptions about noise characteristics, thereby constraining their applicability in real-world scenarios. Inspired by the properties of the Frobenius norm expansion, we discover that incorporating a trace term reduces the optimization goal disparity between self-supervised and supervised methods, thereby enhancing the performance of self-supervised learning. To exploit this insight, we propose a trace-constraint loss function and design the low-trace adaptation Noise2Noise (LoTA-N2N) model that bridges the gap between self-supervised and supervised learning. Furthermore, we have discovered that several existing self-supervised denoising frameworks naturally fall within the proposed trace-constraint loss as subcases. Extensive experiments conducted on natural and confocal image datasets indicate that our method achieves state-of-the-art performance within the realm of zero-shot self-supervised image denoising approaches, without relying on any assumptions regarding the noise. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_12382 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Low-Trace Adaptation of Zero-shot Self-supervised Blind Image Denoising Hu, Jintong Xia, Bin Li, Bingchen Yang, Wenming Image and Video Processing Computer Vision and Pattern Recognition Machine Learning Deep learning-based denoiser has been the focus of recent development on image denoising. In the past few years, there has been increasing interest in developing self-supervised denoising networks that only require noisy images, without the need for clean ground truth for training. However, a performance gap remains between current self-supervised methods and their supervised counterparts. Additionally, these methods commonly depend on assumptions about noise characteristics, thereby constraining their applicability in real-world scenarios. Inspired by the properties of the Frobenius norm expansion, we discover that incorporating a trace term reduces the optimization goal disparity between self-supervised and supervised methods, thereby enhancing the performance of self-supervised learning. To exploit this insight, we propose a trace-constraint loss function and design the low-trace adaptation Noise2Noise (LoTA-N2N) model that bridges the gap between self-supervised and supervised learning. Furthermore, we have discovered that several existing self-supervised denoising frameworks naturally fall within the proposed trace-constraint loss as subcases. Extensive experiments conducted on natural and confocal image datasets indicate that our method achieves state-of-the-art performance within the realm of zero-shot self-supervised image denoising approaches, without relying on any assumptions regarding the noise. |
| title | Low-Trace Adaptation of Zero-shot Self-supervised Blind Image Denoising |
| topic | Image and Video Processing Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2403.12382 |