IP Library › Granted Patent US 12,333,752
Granted Patent B2
US 12,333,752 · App. 17/736,155 · Granted Jun 17, 2025

Image processing apparatus and method, and image capturing apparatus and control method thereof, and storage medium

Inventors: Hidetoshi Tsubaki (Kanagawa, JP); Taisei Mori (Kanagawa, JP)
Assignee: Canon Kabushiki Kaisha
G06T7/593G06T5/73H04N13/282H04N13/296
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 12,333,752
App. No.
17/736,155
Granted
Jun 17, 2025
Kind
B2
Abstract

An image processing apparatus comprises: an acquisition unit that acquires a plurality of different viewpoint images obtained by shooting a same scene from different viewpoints, and acquires at least one parallax image pair having parallax by pupil division; a first generator that generates a first distance image from the parallax image pair; a second generator that generates a second distance image from the plurality of different viewpoint images; and an integrator that integrates the first distance image and the second distance image and generates an integrated distance image.

Claims (55)

1. An image processing apparatus comprising one or more processors and/or circuitry which functions as:

an acquisition unit that acquires a plurality of different viewpoint images obtained by shooting a same scene from different viewpoints, and acquires at least one parallax image pair having parallax by pupil division;

a first generator that generates a first distance image from the parallax image pair;

a second generator that generates a second distance image from the plurality of different viewpoint images; and

an integrator that integrates the first distance image and the second distance image and generates an integrated distance image,

wherein the integrator integrates the first distance image and the second distance image by complementing distance information of an area where a subject is moving among distance information constituting the second distance image with distance information of a same area in the first distance image.

2. The image processing apparatus according to claim 1 , wherein the integrator integrates the first distance image and the second distance image by complementing distance information of an area excluding an area indicating a distance shorter than a predetermined distance, and an area indicating a predetermined range from an in-focus distance among distance information constituting the first distance image with distance information of a same area in the second distance image.

3. The image processing apparatus according to claim 1 , wherein the second generator generates the second distance image based on parallax between the plurality of different viewpoint images.

4. The image processing apparatus according to claim 3 , wherein the second generator generates the second distance image using epipolar geometry based on the plurality of different viewpoint images.

5. The image processing apparatus according to claim 1 , wherein the acquisition unit acquires a plurality of parallax image pairs obtained by shooting a same scene at different positions, and

wherein the image processing apparatus further comprises a third generator that generates a plurality of different viewpoint images from the plurality of parallax image pairs.

6. The image processing apparatus according to claim 5 , wherein the third generator selects one of the plurality of parallax image pairs as a reference parallax image pair and generates the plurality of different viewpoint images by adding images constituting each of the plurality of parallax image pairs except for the reference parallax image pair pixel by pixel.

7. The image processing apparatus according to claim 5 , wherein the third generator keeps one of the plurality of parallax image pairs as a reference parallax image pair as it is, and generates the plurality of different viewpoint images by adding images constituting each of the plurality of parallax image pairs including the reference parallax image pair pixel by pixel.

8. The image processing apparatus according to claim 6 , wherein the third generator sequentially shifts selection of the reference parallax image pair among the plurality of parallax image pairs and generates the plurality of different viewpoint images for each of the sequentially selected reference parallax image pairs, and

wherein the integrator integrates, for each of the sequentially selected reference parallax image pairs, the first distance image generated from the reference parallax image pair and the second distance image generated from the plurality of different viewpoint images corresponding to the reference parallax image pair, and generates a plurality of the integrated distance images.

9. The image processing apparatus according to claim 7 , wherein the third generator sequentially shifts selection of the reference parallax image pair among the plurality of parallax image pairs and generates the plurality of different viewpoint images for each of the sequentially selected reference parallax image pairs, and

wherein the integrator integrates, for each of the sequentially selected reference parallax image pairs, the first distance image generated from the reference parallax image pair and the second distance image generated from the plurality of different viewpoint images corresponding to the reference parallax image pair, and generates a plurality of the integrated distance images.

10. The image processing apparatus according to claim 5 , wherein the third generator performs defocus deblurring processing on the plurality of parallax image pairs and generates the plurality of different viewpoint images from the plurality of parallax image pairs undergone the defocus deblurring processing.

11. The image processing apparatus according to claim 10 , wherein the defocus deblurring processing includes deconvolution processing or maximum a posteriori (MAP) estimation processing performed by estimating defocus kernel, and deep learning processing by end-to-end processing using an encoder-decoder structure.

12. The image processing apparatus according to claim 1 , wherein the acquisition unit acquires a plurality of parallax image pairs obtained by shooting a same scene at different positions,

wherein the first generator generates the first distance image from each of a plurality of predetermined parallax image pairs among the plurality of parallax image pairs, selects one of a plurality of the generated first distance images as a reference first distance image, changes viewpoints of the first distance images other than the reference first distance image, and integrates the first distance images whose viewpoints are changed with the reference first distance image, and

wherein the integrator integrates the integrated first distance image and the second distance image.

13. An image capturing apparatus comprising:

(A) an image processing apparatus comprising one or more processors and/or circuitry which functions as: (1) an acquisition unit that acquires a plurality of different viewpoint images obtained by shooting a same scene from different viewpoints, and acquires at least one parallax image pair having parallax by pupil division; (2) a first generator that generates a first distance image from the parallax image pair; (3) a second generator that generates a second distance image from the plurality of different viewpoint images; and (4) an integrator that integrates the first distance image and the second distance image and generates an integrated distance image; and

(B) an image sensor that shoots the at least one parallax image pair at least as part of the acquisition unit,

wherein the integrator integrates the first distance image and the second distance image by complementing distance information of an area where a subject is moving among distance information constituting the second distance image with distance information of a same area in the first distance image.

14. The image capturing apparatus according to claim 13 , wherein the image sensor shoots the at least one parallax image pair after shooting the plurality of different viewpoint images.

15. The image capturing apparatus according to claim 13 , wherein the image sensor shoots the plurality of different viewpoint images after shooting the at least one parallax image pair.

16. The image capturing apparatus according to claim 13 , wherein the image sensor shoots the plurality of different viewpoint images before and after shooting the at least one parallax image pair.

17. The image capturing apparatus according to claim 13 , wherein the image sensor controls an aperture of a diaphragm for shooting the plurality of different viewpoint images to be smaller than that for shooting the at least one parallax image pairs.

18. The image capturing apparatus according to claim 13 , wherein the image sensor independently sets shooting conditions for shooting the at least one parallax image pairs and for shooting the plurality of different viewpoint images.

19. An image processing method comprising:

acquiring a plurality of different viewpoint images obtained by shooting a same scene from different viewpoints, and acquiring at least one parallax image pair having parallax by pupil division;

generating a first distance image from the parallax image pair;

generating a second distance image from the plurality of different viewpoint images; and

integrating the first distance image and the second distance image to generate an integrated distance image,

wherein the integrating integrates the first distance image and the second distance image by complementing distance information of an area where a subject is moving among distance information constituting the second distance image with distance information of a same area in the first distance image.

20. A non-transitory computer-readable storage medium, the storage medium storing a program that is executable by a computer, wherein the program includes program code for causing the computer to execute an image processing method, the image processing method comprising:

acquiring a plurality of different viewpoint images obtained by shooting a same scene from different viewpoints, and acquiring at least one parallax image pair having parallax by pupil division;

generating a first distance image from the parallax image pair;

generating a second distance image from the plurality of different viewpoint images; and

integrating the first distance image and the second distance image to generate an integrated distance image,

wherein the integrating integrates the first distance image and the second distance image by complementing distance information of an area where a subject is moving among distance information constituting the second distance image with distance information of a same area in the first distance image.

21. An image processing apparatus comprising one or more processors and/or circuitry which functions as:

an acquisition unit that acquires a plurality of different viewpoint images obtained by shooting a same scene from different viewpoints, and acquires at least one parallax image pair having parallax by pupil division;

a first generator that generates a first distance image from the parallax image pair;

a second generator that generates a second distance image from the plurality of different viewpoint images; and

an integrator that integrates the first distance image and the second distance image and generates an integrated distance image,

wherein the integrator integrates the first distance image and the second distance image by complementing distance information of an area excluding an area indicating a distance shorter than a predetermined distance, and an area indicating a predetermined range from an in-focus distance among distance information constituting the first distance image with distance information of a same area in the second distance image.

22. An image processing method comprising:

acquiring a plurality of different viewpoint images obtained by shooting a same scene from different viewpoints, and acquiring at least one parallax image pair having parallax by pupil division;

generating a first distance image from the parallax image pair;

generating a second distance image from the plurality of different viewpoint images; and

integrating the first distance image and the second distance image to generate an integrated distance image,

wherein the integrating integrates the first distance image and the second distance image by complementing distance information of an area excluding an area indicating a distance shorter than a predetermined distance, and an area indicating a predetermined range from an in-focus distance among distance information constituting the first distance image with distance information of a same area in the second distance image.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 9, 2022
From: TSUBAKI, HIDETOSHI; MORI, TAISEI
To: CANON KABUSHIKI KAISHA
Reel/Frame 060143/0977 →
Priority Claims (4)
JP 2021-079246 · May 7, 2021 · national
JP 2021-082597 · May 14, 2021 · national
JP 2021-154713 · Sep 22, 2021 · national
JP 2022-052478 · Mar 28, 2022 · national
Continuity (1)
Related Publication 20220358667A1 · Nov 10, 2022
References Cited (47)
US 8520059B2 · Aoki · 2013 [cited by applicant]
US 9088718B2 · Tsubaki · 2015 [cited by applicant]
US 9167224B2 · Izawa · 2015 [cited by applicant]
US 10547824B2 · Tanaka · 2020 [cited by applicant]
US 10679326B2 · Tanaka · 2020 [cited by applicant]
US 11044453B2 · Tanaka · 2021 [cited by applicant]
US 20100328456A1 · Alakarhu · 2010 [cited by examiner]
US 20110242273A1 · Shimaya · 2011 [cited by examiner]
US 20130010078A1 · Aoki · 2013 [cited by applicant]
US 20130194390A1 · Hirooka · 2013 [cited by applicant]
US 20140341285A1 · Sakurai · 2014 [cited by examiner]
US 20150009299A1 · Izawa · 2015 [cited by applicant]
US 20170148137A1 · Tanaka · 2017 [cited by applicant]
US 20170295355A1 · Tanaka · 2017 [cited by applicant]
US 20180007285A1 · Fang · 2018 [cited by applicant]
US 20180184013A1 · Hamano et al. · 2018 [cited by applicant]
US 20180316909A1 · Tsubaki · 2018 [cited by applicant]
US 20190128669A1 · Nobayashi · 2019 [cited by applicant]
US 20190166349A1 · Park · 2019 [cited by examiner]
US 20190166350A1 · Park · 2019 [cited by examiner]
US 20200120323A1 · Tanaka · 2020 [cited by applicant]
US 20200326609A1 · Tsubaki · 2020 [cited by applicant]
US 20200366882A1 · Okuzawa · 2020 [cited by applicant]
CA 2663084 · 2007 [cited by examiner]
CN 101719286A · 2010 [cited by applicant]
CN 104221370A · 2014 [cited by applicant]
CN 107637067 · 2016 [cited by examiner]
JP 2005257278A · 2005 [cited by applicant]
JP 2011112507A · 2011 [cited by applicant]
JP 2012122911A · 2012 [cited by applicant]
JP 5192096B2 · 2013 [cited by applicant]
JP 2014215261A · 2014 [cited by applicant]
JP 2016085637A · 2016 [cited by applicant]
JP 2017103756A · 2017 [cited by applicant]
JP 2020021126A · 2020 [cited by applicant]
JP 2020191624A · 2020 [cited by applicant]
Kitahara, Translation of CA 2663084 Sep. 18, 2007 (Year: 2007). [cited by examiner]
Horikawa Translation of CN 107637067 Jun. 1, 2016 (Year: 2016). [cited by examiner]
Nov. 29, 2022 Indian Official Action in Indian Patent Appln. No. 202244025968. [cited by applicant]
Nov. 1, 2022 Search Report in Great Britain Patent Appln. No. 2206275.6. [cited by applicant]
Sep. 20, 2023 United Kingdom Official Action in United Kingdom Patent Appln. No. GB2206275.6. [cited by applicant]
“Accurate, Dense, and Robust Multiview Stereopsis”, IEEE Transactions Pattern Analysis and Machine Intelligence, 32(8), pp. 1362-1376 by Furukawa et al. (2010). [cited by applicant]
“Defocus Deblurring Using Dual-Pixel Data”, ECCV2020, Abdullah Abuolaim et al. (2020). [cited by applicant]
“Dual Pixel Exploration: Simultaneous Depth Estimation and Image Restoration” , CVPR2021, Liyuan Pan et al. (2020). [cited by applicant]
“Modeling Defocus-Disparity in Dual-Pixel Sensors ”, ICCP2020, Abhijith Punnappurath et al. (2020). [cited by applicant]
Jul. 29, 2024 Chinese Official Action in Chinese Patent Appln. No. 202210487575.5. [cited by applicant]
Jan. 3, 2025 Chinese Official Action in Chinese Patent Appln. No. 202210487575.5. [cited by applicant]
Cited By (1)
US 12,711,644