paper-with-me

Papers

MM-BSN: Self-Supervised Image Denoising for Real-World with Multi-Mask based on Blind-Spot Network

2023-04-04 · Dan Zhang, Fangfang Zhou, Yuwen Jiang, Zhengming Fu

Recent advances in deep learning have been pushing image denoising techniques to a new level. In self-supervised image denoising, blind-spot network (BSN) is one of the most common methods. However, most of the existing BSN algorithms use a dot-based central mask, which is recognized as inefficient for images with large-scale spatially correlated noise. In this paper, we give the definition of large-noise and propose a multi-mask strategy using multiple convolutional kernels masked in different shapes to further break the noise spatial correlation. Furthermore, we propose a novel self-supervised image denoising method that combines the multi-mask strategy with BSN (MM-BSN). We show that different masks can cause significant performance differences, and the proposed MM-BSN can efficiently fuse the features extracted by multi-masked layers, while recovering the texture structures destroyed by multi-masking and information transmission. Our MM-BSN can be used to address the problem of large-noise denoising, which cannot be efficiently handled by other BSN methods. Extensive experiments on public real-world datasets demonstrate that the proposed MM-BSN achieves state-of-the-art performance among self-supervised and even unpaired image denoising methods for sRGB images denoising, without any labelling effort or prior knowledge. Code can be found in https://github.com/dannie125/MM-BSN.

📄 PDF Abstract BibTeX arXiv:2304.01598

Code (2)

dannie125/mm-bsn 공식 구현 pytorch
secml-lab-vt/EvolvingThreat-DeepfakeImageDetect pytorch

Tasks

DenoisingImage Denoising

Similar Papers 제목 키워드 기반

AP-BSN: Self-Supervised Denoising for Real-World Images via Asymmetric PD and Blind-Spot Network

2022-03-22 · CVPR 2022 1 · Wooseok Lee, Sanghyun Son, Kyoung Mu Lee

Blind-spot network (BSN) and its variants have made significant advances in self-supervised denoising. Nevertheless, they are still bound to synthetic noisy inputs due to less practical assumptions like pixel-wise indepe…

Denoising

Random Sub-Samples Generation for Self-Supervised Real Image Denoising

2023-07-31 · ICCV 2023 1 · Yizhong Pan, Xiao Liu, Xiangyu Liao, Yuanzhouhan Cao 외

With sufficient paired training samples, the supervised deep learning methods have attracted much attention in image denoising because of their superior performance. However, it is still very challenging to widely utiliz…

DenoisingImage Denoising

I2V: Towards Texture-Aware Self-Supervised Blind Denoising using Self-Residual Learning for Real-World Images

2023-02-21 · Kanggeun Lee, Kyungryun Lee, Won-Ki Jeong

Although the advances of self-supervised blind denoising are significantly superior to conventional approaches without clean supervision in synthetic noise scenarios, it shows poor quality in real-world images due to spa…

DenoisingSSIM

Pseudo-Siamese Blind-Spot Transformers for Self-Supervised Real-World Denoising

2025-06-05 · The Annual Conference on Neural Information Processing Systems 2025 6 · Yuhui Quan; Tianxiang Zheng; Hui Ji

Real-world image denoising remains a challenge task. This paper studies self-supervised image denoising, requiring only noisy images captured in a single shot. We revamping the blind-spot technique by leveraging the tran…

DenoisingImage Denoising

Iterative Denoiser and Noise Estimator for Self-Supervised Image Denoising

2023-01-01 · ICCV 2023 1 · Yunhao Zou, Chenggang Yan, Ying Fu

With the emergence of powerful deep learning tools, more and more effective deep denoisers have advanced the field of image denoising. However, the huge progress made by these learning-based methods severely relies o…

DenoisingImage Denoising