IP Library Granted Patent US 11,893,482
Granted Patent B2
US 11,893,482 · App. 16/799,597 · Granted Feb 6, 2024

Image restoration for through-display imaging

Inventors: Yuqian Zhou (Urbana, IL); Timothy Andrew Large (Bellevue, WA); Se Hoon Lim (Bellevue, WA); Neil Emerton (Redmond, WA); Yonghuan David Ren (El Cerrito, CA)
Assignee: Microsoft Technology Licensing, LLC
G06N3/08G06F18/214G06N20/00G06T5/002G06T5/003G06T5/50G06V10/764G06V10/774H04N23/64G06V10/454G06V10/82G06V40/161
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 11,893,482
App. No.
16/799,597
Granted
Feb 6, 2024
Kind
B2
Abstract

Examples are disclosed that relate to the restoration of degraded images acquired via a behind-display camera. One example provides a method of training a machine learning model, the method comprising inputting training image pairs into the machine learning model, each training image pair comprising an undegraded image and a degraded image that represents an appearance of the undegraded image to a behind-display camera, and training the machine learning model using the training image pairs to generate frequency information that is missing from the degraded images.

Claims (9)

1. A method of training a machine learning model, the method comprising:

inputting training image pairs into the machine learning model, the machine learning model comprising a U-shaped neural network comprising a first sub-encoder and a second sub-encoder in parallel with the first sub-encoder, each training image pair comprising an undegraded image and a degraded image that represents an appearance of the undegraded image to a behind-display camera, the degraded image comprising loss of mid-frequency information due to diffraction-related blurring, the mid-frequency information within a range of 2 to 8 cycles per degree; and

training the machine learning model using the training image pairs to generate mid-frequency information to correct for the loss of mid-frequency information due to the diffraction-related blurring, wherein the first sub-encoder is trained to compute residual details and the second sub-encoder is trained to learn content encoding.

2. The method of claim 1 , wherein providing training image pairs to the machine learning model comprises providing the image pairs to a convolutional neural network.

3. The method of claim 1 , wherein the undegraded training image comprises an average of a plurality of repeated captured frames.

4. The method of claim 1 , further comprising acquiring each degraded image via a camera positioned behind a mask.

5. The method of claim 1 , wherein the degraded image comprises an image acquired via a camera array.

6. The method of claim 1 , wherein the training image pair is a part of three or more corresponding training images.

7. The method of claim 1 , further comprising, after training the machine learning model, implementing the machine learning model in a computing device for imaging via a behind-display camera.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 24, 2020
From: ZHOU, YUQIAN; LARGE, TIMOTHY ANDREW; LIM, SE HOON; EMERTON, NEIL; REN, YONGHUAN DAVID
To: MICROSOFT TECHNOLOGY LICENSING, LLC
Reel/Frame 051909/0049 →
Continuity (2)
Provisional Application 62935367 · Nov 14, 2019
Related Publication 20210152734A1 · May 20, 2021
Cited By (4)
US 12,322,073 US 12,393,765 US 12,482,075 US 12,651,320