IP Library › Granted Patent US 12711588
Granted Patent B2
US 12711588 · App. 18/264,120 · Granted Aug 18, 2026

Learning apparatus, moving image generating apparatus, method of generating learned model, moving image generating method, and program

Inventor: Hirotaka Asayama (Tokyo, JP)
Assignee: SONY INTERACTIVE ENTERTAINMENT INC.
G06T5/92G06T5/50G06T2207/10016G06T2207/20081G06T2207/20084G06T2207/20208
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12711588
App. No.
18/264,120
Granted
Aug 18, 2026
Kind
B2
Abstract

A learning apparatus, a method of generating a learned model, and a program are capable of adequately widening the dynamic ranges of various images in a unified fashion. A training data generating section generates, on the basis of a second-class image, a first-class image associated with the second-class image, by referring to associative data where luminance values in a second dynamic range and luminance values in a first dynamic range are associated with each other. A learning section performs a learning process of a machine learning model by using the first-class image and the second-class image associated with the first-class image.

Claims (43)

1 . A moving image generating apparatus comprising:

a processor; and

a storage unit storing programs executable by the processor to perform operations comprising:

generating, based on a first-class video of a first dynamic range, a second-class video, the second-class video being a version of the first-class video with a second dynamic range into which the first dynamic range has been widened, wherein the generating the second-class video comprises:

executing a forward generation process that, by using a learned model and on a basis of a first-class frame image that is a frame of the first-class video and a second-class frame image of a frame immediately before the first-class frame image, generates a second-class frame image of the first-class frame image, the second-class frame image of the frame immediately before the first-class frame image being generated by the learned model;

executing a backward generation process that, by using the learned model and on a basis of the first-class frame image and a second-class frame image of a frame immediately after the first-class frame image, generates a second-class frame image of the first-class frame image, the second-class frame image of the frame immediately after the first-class video being generated by the learned model; and

generating the second-class video using the second-class frame image generated by the forward generation process and the second-class frame image generated by the backward generation process.

2 . The moving image generating apparatus according to claim 1 ,

wherein the operations further comprise:

executing another forward generation process that generates, on a basis of the first-class frame image, a first-class frame image of the frame immediately before the first-class frame image, and the second-class frame image of the frame immediately before the first-class frame image, another second-class frame image of the first-class frame image; and

executing another backward generation process that generates, on a basis of the first-class frame image, a first-class frame image of the frame immediately after the first-class frame image, and the second-class frame image of the frame immediately after the first-class frame image, another second-class frame image of the first-class frame image.

3 . The moving image generating apparatus according to claim 1 , wherein the operations further comprise generating, on a basis of the first-class frame image and the second-class frame image generated by the forward generation process, another second-class frame image associated with the first-class frame image.

4 . The moving image generating apparatus according to claim 1 , wherein the operations further comprise generating, on a basis of the first-class frame image and the second-class frame image generated by the backward generation process, another second-class frame image associated with the first-class frame image.

5 . The moving image generating apparatus according to claim 1 , wherein the second-class video includes the second-class frame image generated by the backward generation process and additional second-class frame images generated by the forward generation process for additional frames of the first-class video.

6 . The moving image generating apparatus according to claim 1 , wherein the operations further comprise generating, with respect to at least one additional frame of the first-class video and on a basis of a second-class frame image of the at least one additional frame generated by the forward generation process and a second-class frame image of the at least one additional frame generated by the backward generation process, a frame image included in the second-class video.

7 . The moving image generating apparatus according to claim 6 , wherein the second-class video is generated where a weighted mean of luminance values of pixels included in the second-class frame image of the at least one additional frame generated by the forward generation process and luminance values of the pixels included in the second-class frame image of the at least one additional frame generated by the backward generation process is set to luminance values of the pixels included in the at least one additional frame.

8 . The moving image generating apparatus according to claim 1 , wherein

the first dynamic range is a standard dynamic range, and

the second dynamic range is a high dynamic range.

9 . A moving image generating method comprising:

generating, based on a first-class video of a first dynamic range, a second-class video, the second-class video being a version of the first-class video with a second dynamic range into which the first dynamic range has been widened, wherein the generating the second-class video comprises:

executing a forward generation process that, by using a learned model and on a basis of a first-class frame image that is a frame of the first-class video and a second-class frame image of a frame immediately before the first-class frame image, generates a second-class frame image of the first-class frame image, the second-class frame image of the frame immediately before the first-class frame image being generated by the learned model;

executing a backward generation process that, by using the learned model and on a basis of the first-class frame image and a second-class frame image of a frame immediately after the first-class frame image, generates a second-class frame image of the first-class frame image, the second-class frame image of the frame immediately after the first-class frame image being generated by the learned model; and

generating the second-class video using the second-class frame image generated by the forward generation process and the second-class frame image generated by the backward generation process.

10 . A non-transitory, computer-readable storage medium containing a computer program, which when executed by a computer causes the computer to carry out actions comprising:

generating, based on a first-class video of a first dynamic range, a second-class video, the second-class video being a version of the first-class video with a second dynamic range into which the first dynamic range has been widened, wherein the generating the second-class video comprises:

executing a forward generation process that, by using a learned model and on a basis of a first-class frame image that is a frame of the first-class video and a second-class frame image of a frame immediately before the first-class frame image, generates a second-class frame image of the first-class frame image, the second-class frame image of the frame immediately before the first-class frame image being generated by the learned model;

executing a backward generation process that, by using the learned model and on a basis of the first-class frame image and a second-class frame image of a frame immediately after the first-class frame image, generates a second-class frame image of the first-class frame image, the second-class frame image of the frame immediately after the first-class frame image being generated by the learned model; and

generating the second-class video using the second-class frame image generated by the forward generation process and the second-class frame image generated by the backward generation process.

11 . The moving image generating method according to claim 9 , further comprising:

executing another forward generation process that generates, on a basis of the first-class frame image, a first-class frame image of the frame immediately before the first-class frame image, and the second-class frame image of the frame immediately before the first-class frame image, another second-class frame image of the first-class frame image; and

executing another backward generation process that generates, on a basis of the first-class frame image, a first-class frame image of the frame immediately after the first-class frame image, and the second-class frame image of the frame immediately after the first-class frame image, another second-class frame image of the first-class frame image.

12 . The moving image generating method according to claim 9 , further comprising generating, on a basis of the first-class frame image and the second-class frame image generated by the forward generation process, another second-class frame image associated with the first-class frame image.

13 . The moving image generating method according to claim 9 , further comprising generating, on a basis of the first-class frame image and the second-class frame image generated by the backward generation process, another second-class frame image associated with the first-class frame image.

14 . The moving image generating method according to claim 9 , wherein the second-class video includes the second-class frame image generated by the backward generation process and additional second-class frame images generated by the forward generation process for additional frames of the first-class video.

15 . The moving image generating method according to claim 9 , further comprising generating, with respect to at least one additional frame of the first-class video and on a basis of a second-class frame image of the at least one additional frame generated by the forward generation process and a second-class frame image of the at least one additional frame generated by the backward generation process, a frame image included in the second-class video.

16 . The moving image generating method according to claim 15 , wherein the second-class video is generated where a weighted mean of luminance values of pixels included in the second-class frame image of the at least one additional frame generated by the forward generation process and luminance values of the pixels included in the second-class frame image of the at least one additional frame generated by the backward generation process is set to luminance values of the pixels included in the at least one additional frame.

17 . The moving image generating method according to claim 9 , wherein the first dynamic range is a standard dynamic range, and the second dynamic range is a high dynamic range.

18 . The non-transitory, computer-readable storage medium according to claim 10 , wherein the actions further comprise:

executing another forward generation process that generates, on a basis of the first-class frame image, a first-class frame image of the frame immediately before the first-class frame image, and the second-class frame image of the frame immediately before the first-class frame image, another second-class frame image of the first-class frame image; and

executing another backward generation process that generates, on a basis of the first-class frame image, a first-class frame image of the frame immediately after the first-class frame image, and the second-class frame image of the frame immediately after the first-class frame image, another second-class frame image of the first-class frame image.

19 . The non-transitory, computer-readable storage medium according to claim 10 , wherein the actions further comprise generating, on a basis of the first-class frame image and the second-class frame image generated by the forward generation process, another second-class frame image associated with the first-class frame image.

20 . The non-transitory, computer-readable storage medium according to claim 10 , wherein the actions further comprise generating, on a basis of the first-class frame image and the second-class frame image generated by the backward generation process, another second-class frame image associated with the first-class frame image.