Author: Kovalenko, Alexey; Demyanenko, Yana
Title: Unsupervised Training of Denoising Networks Cord-id: hmdrms8v Document date: 2021_2_20
ID: hmdrms8v
Snippet: This work explore approach for image denoising of received by CMOS sensor. Proposed pipeline solves the problem of unsupervised training neural network architectures for image denoising which uses datasets without clean data. This approach bases on theoretical background about image restoration proposed by Nvidia researchers. We implemented custom denoising neural network architectures using specifics of noise distribution. Networks are trained on custom images collection.
Document: This work explore approach for image denoising of received by CMOS sensor. Proposed pipeline solves the problem of unsupervised training neural network architectures for image denoising which uses datasets without clean data. This approach bases on theoretical background about image restoration proposed by Nvidia researchers. We implemented custom denoising neural network architectures using specifics of noise distribution. Networks are trained on custom images collection.
Search related documents:
Co phrase search for related documents- Try single phrases listed below for: 1
Co phrase search for related documents, hyperlinks ordered by date