arXiv:2007.01575
공식 코드 · Papers with Code
Ground Truth Free Denoising by Optimal Transport
원문 초록
We present a learned unsupervised denoising method for arbitrary types of data, which we explore on images and one-dimensional signals. The training is solely based on samples of noisy data and examples of noise, which -- critically -- do not need to come in pairs. We only need the assumption that the noise is independent and additive (although we describe how this can be extended). The method rests on a Wasserstein Generative Adversarial Network setting, which utilizes two critics and one generator.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Time-series surrogates from energy consumers generated by machine learning approaches for long-term forecasting scenarios
CWGAN-GP Augmented CAE for Jamming Detection in 5G-NR in Non-IID Datasets
SNRGAN: The Semi Noise Reduction GAN for Image Denoising
Content-Noise Complementary Learning for Medical Image Denoising
PMHLD: Patch Map Based Hybrid Learning DehazeNet for Single Image Haze Removal
Generative Latent Kernel Modeling for Blind Motion Deblurring
토론
이 논문과 연결된 포럼 글이 아직 없습니다.