Automated pixel error detection using an inpainting neural network

Number: 11210774
Published: 2021-12-28
Filed: 2020-03-31
Assignee: Disney Enterprises, Inc.
Inventors: Schroers; Christopher Richard, Djelouah; Abdelaziz, Wang; Sutao, Doggett; Erika Varis
CPC: G06N3/04; G06N3/045; G06N3/0455; G06N3/0464; G06T5/50; G06T5/60; G06T5/77; G06T7/0002; G06T9/002
Verdict: Set aside pixel error QC tool, media production
Source: Google Patents · FreePatentsOnline

Abstract

According to one implementation, a pixel error detection system includes a hardware processor and a system memory storing a software code. The hardware processor is configured to execute the software code to receive an input image, to mask, using an inpainting neural network (NN), one or more patch(es) of the input image, and to inpaint, using the inpainting NN, the masked patch(es) based an input image pixels neighboring each of the masked patch(es). The hardware processor is configured to further execute the software code to generate, using the inpainting NN, a residual image based on differences between the inpainted masked patch(es) and the patch(es) in the input image and to identify one or more anomalous pixel(s) in the input image using the residual image.

Background

BACKGROUND (1) Pixel errors in images occur with regularity but can be difficult and costly to identify. For example, anomalous pixels in video frames can be introduced by many different processes within a video production pipeline. A final quality procedure for detecting and correcting such errors is typically done before the video undergoes final release. (2) In the conventional art, anomalous pixel detection is usually performed by human inspectors. Generally, those human inspectors are tasked with checking every single frame of each video several hundreds of times before its final distribution. Due to this intense reliance on human participation, the conventional approach to pixel error detection and correction is undesirably expensive and time consuming. Accordingly, there is a need in the art for an image correction solution enabling accurate detection of anomalous pixel errors using an automated process. SUMMARY (3) There are provided systems and methods for performing automated pixel error detection using an inpainting neural network, substantially as shown in and/or described in connection with at least one of the figures, and as set forth more completely in the claims.

Claims

1. An automated pixel error detection system comprising: a hardware processor; and a system memory storing a software code; the hardware processor configured to execute the software code to: receive an input image; mask, using an inpainting neural network (NN), one or more patches of the input image; inpaint, using the inpainting NN, the one or more masked patches based on a plurality of input image pixels neighboring each of the one or more masked patches; generate, using the inpainting NN, a residual image based on differences between the inpainted one or more masked patches and the one or more patches in the input image; and identify at least one anomalous pixel in the input image using the residual image. || 11. A method for use by an automated pixel error detection system including a hardware processor and a system memory storing a software code, the method comprising: receiving, by the software code executed by the hardware processor, an input image; masking, by the software code executed by the hardware processor and using an inpainting neural network (NN), one or more patches of the input image; inpainting, by the software code executed by the hardware processor and using the inpainting NN, the one or more masked patches based on a plurality of input image pixels neighboring each of the one or more masked patches; generating, by the software code executed by the hardware processor and using the inpainting NN, a residual image based on differences between the inpainted one or more masked patches and the one or more patches in the input image; and identifying, by the software code executed by the hardware processor, at least one anomalous pixel in the input image using the residual image.