Image Deconvolution via Noise-Tolerant Self-Supervised Inversion
We propose a general framework for solving inverse problems in the presence of noise that requires no signal prior, no noise estimate, and no clean training data. We only require that the forward model be available and that the noise be statistically independent across measurement dimensions. We build upon the theory of $\mathcal{J}$-invariant functions (Batson & Royer 2019, arXiv:1901.11365) and show how self-supervised denoising \emph{\`a la} Noise2Self is a special case of learning a noise-tolerant pseudo-inverse of the identity. We demonstrate our approach by showing how a convolutional neural network can be taught in a self-supervised manner to deconvolve images and surpass in image quality classical inversion schemes such as Lucy-Richardson deconvolution.
Code (1)
Tasks
DenoisingImage DeconvolutionSimilar Papers 제목 키워드 기반
Self-Supervised Single-Image Deconvolution with Siamese Neural Networks
Inverse problems in image reconstruction are fundamentally complicated by unknown noise properties. Classical iterative deconvolution approaches amplify noise and require careful parameter selection for an optimal trade-…
Image DeconvolutionImage ReconstructionNonblind image deconvolution via leveraging model uncertainty in an untrained deep neural network
Nonblind image deconvolution (NID) is about restoring the latent image with sharp details from a noisy blurred one using a known blur kernel. This paper presents a dataset-free deep learning approach for NID using untr…
Bayesian InferenceImage DeconvolutionPhoton-Limited Blind Deconvolution using Unsupervised Iterative Kernel Estimation
Blind deconvolution is a challenging problem, but in low-light it is even more difficult. Existing algorithms, both classical and deep-learning based, are not designed for this condition. When the photon shot noise is st…
Image RestorationImplicit Neural Representations for Deconvolving SAS Images
Synthetic aperture sonar (SAS) image resolution is constrained by waveform bandwidth and array geometry. Specifically, the waveform bandwidth determines a point spread function (PSF) that blurs the locations of point sca…
Image DeconvolutionSINR: Deconvolving Circular SAS Images Using Implicit Neural Representations
Circular Synthetic aperture sonars (CSAS) capture multiple observations of a scene to reconstruct high-resolution images. We can characterize resolution by modeling CSAS imaging as the convolution between a scene's under…