2 citations · 3 across the 4 of their papers we have counts for
Showing cs.CVShow all
2 papers · 1 filter
cs.CV2023
Self-Supervised Single-Image Deconvolution with Siamese Neural Networks
Mikhail Papkov, Kaupo Palo, Leopold Parts
Inverse problems in image reconstruction are fundamentally complicated by unknown noise properties. Classical iterative deconvolution approaches amplify noise and require careful p…
cs.CV2023★ 2 cited
SwinIA: Self-Supervised Blind-Spot Image Denoising without Convolutions
Mikhail Papkov, Pavel Chizhov, Leopold Parts
Self-supervised image denoising implies restoring the signal from a noisy image without access to the ground truth. State-of-the-art solutions for this task rely on predicting mask…