A cross Transformer for image denoising
Preprint
Abstract
Deep convolutional neural networks (CNNs) depend on feedforward and feedback ways to obtain good performance in image denoising. However, how to obtain effective structural information via CNNs to efficiently represent given noisy images is key for complex scenes. In this paper, we propose a cross Transformer denoising CNN (CTNet) with a serial block (SB), a parallel block (PB), and a residual block (RB) to obtain clean images for complex scenes. A SB uses an enhanced residual architecture to deeply search structural information for image denoising. To avoid loss of key information, PB uses three heterogeneous networks to implement multiple interactions of multi-level features to broadly search for extra information for improving the adaptability of an obtained denoiser for complex scenes. Also, to improve denoising performance, Transformer mechanisms are embedded into the SB and PB to extract complementary salient features for effectively removing noise in terms of pixel relations. Finally, a RB is applied to acquire clean images. Experiments illustrate that our CTNet is superior to some popular denoising methods in terms of real and synthetic image denoising. It is suitable to mobile digital devices, i.e., phones. Codes can be obtained at https://github.com/hellloxiaotian/CTNet.Keywords
All Related Versions
This publication has 35 references indexed in Scilit:
- A model-driven network for guided image denoisingInformation Fusion, 2022
- Designing and training of a dual CNN for image denoisingKnowledge-Based Systems, 2021
- Deep learning on image denoising: An overviewNeural Networks, 2020
- An overview on spectral and spatial information fusion for hyperspectral image classification: Current trends and challengesInformation Fusion, 2020
- Attention-guided CNN for image denoisingNeural Networks, 2020
- A nonsubsampled countourlet transform based CNN for real image denoisingSignal Processing: Image Communication, 2020
- Image denoising using deep CNN with batch renormalizationNeural Networks, 2020
- Dilated Residual Networks with Symmetric Skip Connection for image denoisingNeurocomputing, 2019
- Low‐dose CT for the detection and classification of metastatic liver lesions: Results of the 2016 Low Dose CT Grand ChallengeMedical Physics, 2017
- Efficient algorithms for finding depth-first and breadth-first search trees in permutation graphsInformation Processing Letters, 1994