Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2402.18192 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910346946543616 |
|---|---|
| author | Ni, Zhangkai Wu, Juncheng Wang, Zian Yang, Wenhan Wang, Hanli Ma, Lin |
| author_facet | Ni, Zhangkai Wu, Juncheng Wang, Zian Yang, Wenhan Wang, Hanli Ma, Lin |
| contents | This paper aims to address a common challenge in deep learning-based image transformation methods, such as image enhancement and super-resolution, which heavily rely on precisely aligned paired datasets with pixel-level alignments. However, creating precisely aligned paired images presents significant challenges and hinders the advancement of methods trained on such data. To overcome this challenge, this paper introduces a novel and simple Frequency Distribution Loss (FDL) for computing distribution distance within the frequency domain. Specifically, we transform image features into the frequency domain using Discrete Fourier Transformation (DFT). Subsequently, frequency components (amplitude and phase) are processed separately to form the FDL loss function. Our method is empirically proven effective as a training constraint due to the thoughtful utilization of global information in the frequency domain. Extensive experimental evaluations, focusing on image enhancement and super-resolution tasks, demonstrate that FDL outperforms existing misalignment-robust loss functions. Furthermore, we explore the potential of our FDL for image style transfer that relies solely on completely misaligned data. Our code is available at: https://github.com/eezkni/FDL |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_18192 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Misalignment-Robust Frequency Distribution Loss for Image Transformation Ni, Zhangkai Wu, Juncheng Wang, Zian Yang, Wenhan Wang, Hanli Ma, Lin Computer Vision and Pattern Recognition Image and Video Processing This paper aims to address a common challenge in deep learning-based image transformation methods, such as image enhancement and super-resolution, which heavily rely on precisely aligned paired datasets with pixel-level alignments. However, creating precisely aligned paired images presents significant challenges and hinders the advancement of methods trained on such data. To overcome this challenge, this paper introduces a novel and simple Frequency Distribution Loss (FDL) for computing distribution distance within the frequency domain. Specifically, we transform image features into the frequency domain using Discrete Fourier Transformation (DFT). Subsequently, frequency components (amplitude and phase) are processed separately to form the FDL loss function. Our method is empirically proven effective as a training constraint due to the thoughtful utilization of global information in the frequency domain. Extensive experimental evaluations, focusing on image enhancement and super-resolution tasks, demonstrate that FDL outperforms existing misalignment-robust loss functions. Furthermore, we explore the potential of our FDL for image style transfer that relies solely on completely misaligned data. Our code is available at: https://github.com/eezkni/FDL |
| title | Misalignment-Robust Frequency Distribution Loss for Image Transformation |
| topic | Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2402.18192 |