Training method of reflection image generation model and reflection removal model
A technology for reflecting images and generating models, which is applied in the field of image processing and can solve the problem that sample images cannot represent complex and real scenes.
Pending Publication Date: 2021-05-14
SUZHOU KEDA TECH
View PDF3 Cites 3 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0007] In view of this, an embodiment of the present invention provides a reflection image generation model and a reflection removal model training method to solve the problem that the sample image obtained through coefficient fusion is difficult to represent a complex and real scene
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0088] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments It is a part of embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative efforts belong to the protection scope of the present invention.
[0089] In the training method of the reflection image generation model described in the embodiment of the present invention, the sample image involved may be a reflection image of a car window, or a reflection image of an electronic device, or other reflection images, etc., which are applied here There are no restrictions on the scene. Specifically, the ...
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
Login to View More Abstract
The invention relates to the technical field of image processing, in particular to a training method of a reflection image generation model and a reflection removal model, and the training method of the reflection image generation model comprises the steps: obtaining any non-reflection sample image and any reflection sample image; inputting the reflection sample image into a reflection removal model to obtain a predicted non-reflection image, and obtaining a predicted reflection layer image feature by using the reflection sample image and the predicted non-reflection image; inputting the predicted reflection layer image features and the non-reflection sample image into a reflection image generation model to obtain a predicted reflection image; and calculating a loss function based on the predicted non-reflection image and the predicted reflection image, and training a reflection removal model and a reflection image generation model to obtain a target reflection image generation model. The non-paired non-reflection sample image and reflection sample image are used for model training, and real data are added for modeling, so that the reflection image generation model has excellent generalization ability.
Description
technical field [0001] The invention relates to the technical field of image processing, in particular to a reflection image generation model and a training method for a reflection removal model. Background technique [0002] When taking images or videos through mirrors, the images often contain mirror-reflected objects, seriously affecting the quality of the presented images. With the wide application of deep learning methods in the direction of image processing, the reflection of reflection images can be removed by means of neural networks, so as to obtain non-reflection images. [0003] During the training of the neural network, pairs of sample images are required, ie, reflected images and corresponding non-reflected images. However, in real scenes, it is difficult to obtain paired sample images. Generally, various linear or nonlinear methods are used to fuse the non-reflective image and the image of the reflective layer to form an image with reflection. For example, an...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/514G06T5/00G06N3/04G06N3/08
CPCG06T7/514G06N3/04G06N3/08G06T2207/20081G06T5/77G06T5/70
Inventor 汪磊李瑮毛晓蛟
Owner SUZHOU KEDA TECH