# US 2026/0228867 A1 · Methods and apparatuses for film grain analysis and synthesis

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0228867 A1
- Document ID: US20260228867A1
- Status: Published application
- Kind: A1
- Application number: 19/151,222
- Filed: 2024-01-22
- Published: 2026-08-06
- Earliest claimed: 2023-01-27
- Assignees: InterDigital CE Patent Holdings, SAS
- Applicants: InterDigital CE Patent Holdings, SAS
- Inventors: Claire-Helene Demarty; Zoubida Ameur; Olivier Le Meur; Daniel Ménard; Edouard Francois
- Web page: https://patentgrep.com/patent/US20260228867A1

## CPC

- G06T 5/77: Retouching; Inpainting; Scratch removal
- H04N 19/85: using pre-processing or post-processing specially adapted for video compression
- G06N 3/0455: Auto-encoder networks; Encoder-decoder networks
- G06N 3/094: Adversarial learning
- G06T 5/60: using machine learning, e.g. neural networks
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A method is disclosed that comprises obtaining (S800) an image. A film grain style vector representative of characteristics of film grain contained in the obtained image. The style vector is obtained (S802) by using a first neural network(S) with the obtained image as input, the first 5 neural network being a network trained to output a film grain style vector from an image.

## Claims

### Claim 1

A method comprising:
obtaining an image; and
obtaining a film grain style vector representative of characteristics of film grain contained in the obtained image by using a first neural network with the obtained image as input, the first neural network being a network trained to output a film grain style vector from an image.

### Claim 2 (depends on 1)

The method of claim 1, comprising:
obtaining another image; and
reconstructing a grainy image by using a second neural network with the another image and the obtained film grain style vector as inputs, the second neural network being a network trained to output a grainy image from a film grain style vector and an image.

### Claim 3

A method comprising:
obtaining an image and a film grain style vector, the film grain style vector being representative of characteristics of film grain; and
reconstructing a grainy image by using a second neural network with the obtained image and the obtained film grain style vector as inputs, the second neural network being a network trained to output a grainy image from a film grain style vector and an image.

### Claim 4

A method comprising:
obtaining an image;
obtaining a film grain style vector representative of characteristics of a film grain by using a third neural network with a latent code as input, the third neural network being a network trained to output a film grain style vector from a latent code; and
reconstructing a grainy image by using a second neural network on the obtained image and the film grain style vector, the second neural network being a network trained to output a grainy image from a film grain style vector and an image.

### Claim 5

A method comprising learning jointly a first neural network, a second neural network using a discriminator neural network from a dataset comprising N different grain free images and, for each of the N grain free images, M grainy versions of each grain free image, N and M being integers, said first neural network being a network trained to output a film grain style vector from an image and said second neural network being a network trained to output a grainy image from a film grain style vector and an image.

### Claim 6 (depends on 5)

The method of claim 5, wherein N=148694 and M=5.

### Claim 7 (depends on 5, 6)

The method of any one of claims 5 to 6, wherein learning jointly the first neural network, the second neural network using a discriminator neural network comprises, for a triplet of a grain free image, a first grainy version and a second grainy version of the grain free image:
a first forward pass comprising using the first neural network with the first grainy version as input to output a first film grain style vector and with the second grainy version as input to output a second film grain style vector, using the second neural network with the grain free image and the first film grain style vector as inputs to output a first grainy image and with the grain free image and the second film grain style vector as inputs to output a second grainy image, using the discriminator neural network with the first grainy version and with the first grainy image as inputs or using the discriminator neural network with a first concatenation of the grain free image and a predicted grain map and a second concatenation of the grain free image and a reference grain map as inputs wherein the predicted grain map is computed as a difference between the first grainy image and the grain free image and wherein the reference grain map is computed as a difference between the first grainy version and the grain free image, using the first neural network with the first grainy image as input to output a third film grain style vector and with the second grainy image as input to output a fourth film grain style vector; and deriving a first global loss function from the outputs; and
a first backward pass to update at least one neural network among the first neural network, the second neural network and the discriminator neural network by backward propagating the first global loss function.

### Claim 8 (depends on 7)

The method of claim 7, wherein learning jointly a first neural network, a second neural network using a discriminator neural network comprises learning jointly a first neural network, a second neural network and a third neural network using a discriminator neural network, the third neural network being a network trained to output a film grain style vector from a latent code.

### Claim 9 (depends on 8)

The method of claim 8, wherein learning jointly the first neural network, the second neural network, the third neural network using a discriminator neural network further comprises:
a second forward pass comprising using the third neural network with a first latent code as input to output a fifth film grain style vector and with a second latent code as input to output a sixth film grain style vector, the first and second latent codes being sampled randomly, using the second neural network with the grain free image and the fifth film grain style vector as inputs to output a third grainy image and with the grain free image and the sixth film grain style vector as inputs to output a fourth grainy image, using the discriminator neural network with the first grainy version and with the third grainy image as inputs or using the discriminator neural network with a first concatenation of the grain free image and a predicted grain map and a second concatenation of the grain free image and a reference grain map as inputs wherein the predicted grain map is computed as a difference between the first grainy image and the grain free image and wherein the reference grain map is computed as a difference between the first grainy version and the grain free image, using the first neural network with the third grainy image as input to output a seventh film grain style vector and with the fourth grainy image as input to output an eighth film grain style vector; and deriving a second global loss function from the outputs; and
a second backward pass to update at least one neural network among the first neural network, the second neural network, the third neural network- and the discriminator neural network by backward propagating the second global loss function.

### Claim 10 (depends on 9)

The method of claim 9, wherein the first forward and backward passes followed by the second forward and backward passes are repeated with a new set of values.

### Claim 11 (depends on 7)

The method of claim 7, wherein the first global loss function is a sum of elementary first loss functions, at least one first elementary loss function being defined to ensure that a cosine similarity between the first and second film grain style vectors (s_ref1, s_ref2) is close to the cosine similarity between the third and fourth film grain style vectors (ŝ_ref1, ŝ_ref2).

### Claim 12 (depends on 11)

The method of claim 11, wherein at least another one first elementary loss function being defined to ensure that the first grainy image is close to the first grainy version.

### Claim 13 (depends on 9)

The method of claim 9, wherein the second global loss function is a sum of elementary second loss functions comprising at least one elementary second loss function defined to ensure that a cosine similarity between the first and second latent codes is close to the cosine similarity between the fifth and sixth film grain style vectors.

### Claim at position 14

14-18. (canceled)
