Improved Self-Supervised Deep Image Denoising
We describe techniques for training high-quality image denoising models that require only single instances of corrupted images as training data. Inspired by a recent technique that removes the need for supervision through image pairs by employing networks with a "blind spot" in the receptive field, we address two of its shortcomings: inefficient training and poor final denoising performance. This is achieved through a novel blind-spot convolutional network architecture that allows efficient self-supervised training, as well as application of Bayesian distribution prediction on output colors. Together, they bring the self-supervised model on par with fully supervised deep learning techniques in terms of both quality and training speed in the case of i.i.d. Gaussian noise.
Code (0)
등록된 구현이 없습니다.
Tasks
DenoisingImage DenoisingSimilar Papers 제목 키워드 기반
Self2Seg: Single-Image Self-Supervised Joint Segmentation and Denoising
We develop Self2Seg, a self-supervised method for the joint segmentation and denoising of a single image. To this end, we combine the advantages of variational segmentation with self-supervised deep learning. One major b…
DenoisingImage DenoisingSegmentationSelf-Supervised Poisson-Gaussian Denoising
We extend the blindspot model for self-supervised denoising to handle Poisson-Gaussian noise and introduce an improved training scheme that avoids hyperparameters and adapts the denoiser to the test data. Self-supervised…
DenoisingImage DenoisingSelf-supervised denoising of raw tomography detector data for improved image reconstruction
Ultrafast electron beam X-ray computed tomography produces noisy data due to short measurement times, causing reconstruction artifacts and limiting overall image quality. To counteract these issues, two self-supervised d…
Image ReconstructionSelf-supervised Dynamic CT Perfusion Image Denoising with Deep Neural Networks
Dynamic computed tomography perfusion (CTP) imaging is a promising approach for acute ischemic stroke diagnosis and evaluation. Hemodynamic parametric maps of cerebral parenchyma are calculated from repeated CT scans of …
DenoisingImage DenoisingSelf-supervised OCT Image Denoising with Slice-to-Slice Registration and Reconstruction
Strong speckle noise is inherent to optical coherence tomography (OCT) imaging and represents a significant obstacle for accurate quantitative analysis of retinal structures which is key for advances in clinical diagnosi…
DenoisingImage DenoisingSelf-Supervised Learning