Image processing method and device, and computer readable storage medium

An image processing and computer technology, applied in the field of image processing, can solve the problems of increasing storage space, increasing GPU, etc., to achieve the effect of reducing image storage space, saving bandwidth consumption, and improving restoration accuracy

Inactive Publication Date: 2019-08-30
BEIJING BYTEDANCE NETWORK TECH CO LTD
View PDF5 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

When making HDR images, images with different exposures can be superimposed in the form of multiple exposures to approximate the true brightness of the scene, but the light intensity range of this image will exceed 1, which will increase storage space and increase GPU (Graphics Processing Unit, graphics processing unit) bandwidth

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Image processing method and device, and computer readable storage medium
  • Image processing method and device, and computer readable storage medium
  • Image processing method and device, and computer readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0080] In order to solve the technical problems of increasing the storage space and increasing the bandwidth of the graphics processor caused by the illumination intensity range of the high dynamic range image exceeding 1 in the prior art, an embodiment of the present disclosure provides an image processing method. Such as figure 1 As shown, the image processing method mainly includes the following steps S11 to S13. in:

[0081] Step S11: Acquire the original high dynamic range image.

[0082] Wherein, the original high dynamic range image may be a high dynamic range image stored in a database in advance, or a high dynamic range image converted in real time by using an existing method. The pixel values ​​of the pixels in the original high dynamic range image range from 0 to 255, including pixels with pixel values ​​greater than 1, and / or, the original high dynamic range image may be a linear transformation image.

[0083] Step S12: Perform nonlinear transformation on the or...

Embodiment 2

[0100] In order to solve the technical problems of increasing the storage space and increasing the bandwidth of the graphics processor caused by the illumination intensity range of the high dynamic range image exceeding 1 in the prior art, the embodiment of the present disclosure also provides an image processing method, such as Figure 2a shown, including:

[0101] S21: Acquire a target high dynamic range image.

[0102] The executor of this embodiment is a low dynamic range shooting device, such as a smart phone, a wearable device, and the like.

[0103] Wherein, the target high dynamic range image is obtained by using the image processing method described in the first embodiment above.

[0104] S22: Decompress the pixel value of each pixel in the target high dynamic range image to obtain a nonlinear transformed image.

[0105] Wherein, the non-linearly transformed image in this embodiment corresponds to the non-linearly transformed image in the first embodiment above, and...

Embodiment 3

[0123] In order to solve the technical problems of increasing the storage space and increasing the bandwidth of the graphics processor caused by the illumination intensity range of the high dynamic range image exceeding 1 in the prior art, an embodiment of the present disclosure provides an image processing device. The device can execute the steps in the image processing method embodiment described in the first embodiment above. Such as image 3 As shown, the device mainly includes: an original image acquisition module 31, a nonlinear conversion module 32, and an image compression module 33; wherein,

[0124] The original image acquisition module 31 is used to acquire the original high dynamic range image;

[0125] The nonlinear conversion module 32 is used for performing nonlinear conversion on the original high dynamic range image to obtain a nonlinear conversion image;

[0126] The image compression module 33 is used to compress the pixel value of each pixel in the non-li...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses an image processing method and device, electronic equipment and a computer readable storage medium. The image processing method comprises the steps: obtaining an original highdynamic range image; performing nonlinear transformation on the original high dynamic range image to obtain a nonlinear transformation image; and compressing the pixel value of each pixel point in thenonlinear transformation image to be between 0 and 1 to obtain a target high-dynamic-range image. According to the embodiment of the invention, an original high-dynamic-range image is converted intoa nonlinear transformation image; the pixel value of each pixel point in the nonlinear transformation image is compressed to be between 0 and 1; and the pixel value of the target high dynamic range image is kept between 0 and 1, so that the image storage space can be reduced, and the restoration precision of the high dynamic range rendering effect can be improved under the condition that the bandwidth of the image processor is limited, and the bandwidth consumption of the image processor can be saved by a half while the high dynamic range rendering effect precision can be approximately restored.

Description

technical field [0001] The present disclosure relates to the technical field of image processing, and in particular to an image processing method, device and computer-readable storage medium. Background technique [0002] HDR (High-Dynamic Range, high dynamic range) images, compared with ordinary images, can provide more dynamic range and image details, according to different exposure time LDR (Low-Dynamic Range, low dynamic range) images, using Each exposure time corresponds to the LDR image with the best details to synthesize the final HDR image, which can better reflect the visual effect in the real environment. [0003] Since the camera film is an LDR acquisition device, the LDR acquisition device will keep the brightness of the light in the range of 0-1. When making HDR images, images with different exposures can be superimposed in the form of multiple exposures to approximate the true brightness of the scene, but the light intensity range of this image will exceed 1, ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06T5/00
CPCG06T5/009
Inventor 郑屹王璨
Owner BEIJING BYTEDANCE NETWORK TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap