Sample-Based Video Denoising

Number: 20180260936
Published: 2018-09-13
Filed: 2017-06-22
Assignee: Disney Enterprises, Inc.
Inventors: Schroers; Christopher et al.
CPC: G06T1/20; G06T5/20; G06T5/70; G06T5/73; H04N5/21; H04N5/213
Verdict: Set aside video-signal denoising enhancement, codec-adjacent plumbing
Source: Google Patents · FreePatentsOnline

Abstract

According to one implementation, a video processing system includes a computing platform having a hardware processor and a system memory storing a sample-based video denoising software code. The hardware processor executes the sample-based video denoising software code to receive a video sequence, and select a reference frame of the video sequence to denoise. For each pixel of the reference frame, the hardware processor executes the sample-based video denoising software code to map the pixel to a sample pixel in each of other frames of the video sequence, identify a first confidence value corresponding to each of the sample pixels based on the mapping, identify a second confidence value corresponding to each of the sample pixels based on the frame that includes the sample pixel, and denoise the pixel based on a weighted combination of the sample pixels determined using the first confidence values and the second confidence values.

Background

BACKGROUND

Due to the popularity of video as an entertainment medium, ever more video content, including high definition (HD) and Ultra HD video content is being produced and made available to consumers. One fundamental challenge encountered in video processing is video denoising, which is the removal of noise from video images that is inevitably generated as video is produced. The object of denoising is to remove such noise without destroying small scale features included in the video images.

One technique for denoising video is performed in three-dimensional (3D) “scene space,” in which video pixels are processed according to their 3D positions. Scene space based denoising relies on depth reconstruction, which limits that approach to static scenes with significant camera motion. However, in practice, most video sequences feature many dynamic moving objects, and often little or no camera motion, making depth reconstruction impossible.SUMMARY

There are provided sample-based video denoising systems and methods, 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. A video processing system comprising: a computing platform including a hardware processor and a system memory; a sample-based video denoising software code stored in the system memory; the hardware processor configured to execute the sample-based video denoising software code to: receive a video sequence; select a reference frame of the video sequence to denoise; for each pixel of the reference frame: map the pixel to a sample pixel in each of a plurality of other frames of the video sequence; identify a first confidence value corresponding to each of the sample pixels, based on the mapping; identify a second confidence value corresponding to each of the sample pixels, based on the frame that includes the sample pixel; and denoise the pixel based on a weighted combination of the sample pixels determined using the first confidence values and the second confidence values. 8. A method for use by a video processing system including a computing platform having a hardware processor and a system memory storing a sample-based video denoising software code, the method comprising: receiving, using the hardware processor, a video sequence; selecting, using the hardware processor, a reference frame of the video sequence to denoise; for each pixel of the reference frame: mapping, using the hardware processor, the pixel to a sample pixel in each of a plurality of other frames of the video sequence; identifying, using the hardware processor, a first confidence value corresponding to each of the sample pixels, based on the mapping; identifying, using the hardware processor, a second confidence value corresponding to each of the sample pixels, based on the frame that includes the sample pixel; and denoising, using the hardware processor, the pixel based on a weighted combination of the sample pixels determined using the first confidence values and the second confidence values. 15. A computer-readable non-transitory medium having stored thereon instructions, which when executed by a hardware processor, instantiate a method comprising: receiving a video sequence; selecting a reference frame of the video sequence to denoise; for each pixel of the reference frame: mapping the pixel to a sample pixel in each of a plurality of other frames of the video sequence; identifying a first confidence value corresponding to each of the sample pixels, based on the mapping; identifying a second confidence value corresponding to each of the sample pixels, based on the frame that includes the sample pixel; and denoising the pixel based on a weighted combination of the sample pixels determined using the first confidence values and the second confidence values.