US 2026/0228934 A1 · METHOD OF GENERATING SYNTHETIC NOISY IMAGE AND SYSTEM PERFORMING THE SAME

Abstract

A method of generating an image in which noise is synthesized by a self-noise synthesis system includes generating a diffusion noisy image by adding Gaussian noise to a noisy image, generating noise embedding by receiving a pair of the diffusion noisy image and a clean image as input, generating first guidance embedding by receiving a pair of a guidance noisy image and a guidance clean image as input, generating second guidance embedding by combining the first guidance embedding and time embedding, generating a prediction vector by receiving the noise embedding and the second guidance embedding as input, and generating a synthetic noisy image based on the prediction vector. A large quantity of noise datasets is generated by utilizing a small quantity of noise datasets.

Claims10

Dependent claims

A method of generating a synthetic noisy image, a self-noise synthesis system generating an image in which noise is synthesized, the method comprising:

generating a diffusion noisy image by adding Gaussian noise to a noisy image;
generating noise embedding by receiving a pair of the diffusion noisy image and a clean image as input;
generating first guidance embedding by receiving a pair of a guidance noisy image and a guidance clean image as input;
generating second guidance embedding by combining the first guidance embedding and time embedding;
generating a prediction vector by receiving the noise embedding and the second guidance embedding as input;
and
generating a synthetic noisy image based on the prediction vector.

4 more elements

Dependencies are inferred from the claim text.

Method of generating synthetic noisy image and system performing the same

Life of this patent

Method of generating synthetic noisy image and system performing the same

Life of this patent

Abstract

Claims10