arXiv Open Access 2022

DnSwin: Toward Real-World Denoising via Continuous Wavelet Sliding-Transformer

Hao Li Zhijing Yang Xiaobin Hong Ziying Zhao Junyang Chen +2 lainnya
Lihat Sumber

Abstrak

Real-world image denoising is a practical image restoration problem that aims to obtain clean images from in-the-wild noisy inputs. Recently, the Vision Transformer (ViT) has exhibited a strong ability to capture long-range dependencies, and many researchers have attempted to apply the ViT to image denoising tasks. However, a real-world image is an isolated frame that makes the ViT build long-range dependencies based on the internal patches, which divides images into patches, disarranges noise patterns and damages gradient continuity. In this article, we propose to resolve this issue by using a continuous Wavelet Sliding-Transformer that builds frequency correspondences under real-world scenes, called DnSwin. Specifically, we first extract the bottom features from noisy input images by using a convolutional neural network (CNN) encoder. The key to DnSwin is to extract high-frequency and low-frequency information from the observed features and build frequency dependencies. To this end, we propose a Wavelet Sliding-Window Transformer (WSWT) that utilizes the discrete wavelet transform (DWT), self-attention and the inverse DWT (IDWT) to extract deep features. Finally, we reconstruct the deep features into denoised images using a CNN decoder. Both quantitative and qualitative evaluations conducted on real-world denoising benchmarks demonstrate that the proposed DnSwin performs favorably against the state-of-the-art methods.

Topik & Kata Kunci

Penulis (7)

H

Hao Li

Z

Zhijing Yang

X

Xiaobin Hong

Z

Ziying Zhao

J

Junyang Chen

Y

Yukai Shi

J

Jinshan Pan

Format Sitasi

Li, H., Yang, Z., Hong, X., Zhao, Z., Chen, J., Shi, Y. et al. (2022). DnSwin: Toward Real-World Denoising via Continuous Wavelet Sliding-Transformer. https://arxiv.org/abs/2207.13861

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2022
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓