Apparatus and method for determining three dimensional data based on an image of a patterned substrate

Patent metadata

Field	Value
Publication number	US-12567164-B2
Application number	US-202118266792-A
Country	US
Kind code	B2
Filing date	Nov 24, 2021
Priority date	Dec 15, 2020
Publication date	Mar 3, 2026
Grant date	Mar 3, 2026

Abstract

A system, method, and apparatus for determining three-dimensional (3D) information of a structure of a patterned substrate. The 3D information can be determined using one or more models configured to generate 3D information (e.g., depth information) using only a single image of a patterned substrate. In a method, the model is trained by obtaining a pair of stereo images of a structure of a patterned substrate. The model generates, using a first image of the pair of stereo images as input, disparity data between the first image and a second image, the disparity data being indicative of depth information associated with the first image. The disparity data is combined with the second image to generate a reconstructed image corresponding to the first image. Further, one or more model parameters are adjusted based on the disparity data, the reconstructed image, and the first image.

First claim

The invention claimed is:

1 . A non-transitory computer-readable medium comprising instructions therein that, when executed by one or more processors, cause the one or more processors to at least:
receive, via a scanning electron microscope (SEM) tool, a single SEM image of a structure patterned on a substrate; input the SEM image to a convolutional neural network (CNN) to predict disparity data associated with the SEM image, the CNN trained by:
obtaining, via the SEM tool, of a stereo pair of SEM images of a patterned substrate, the stereo pair including a first SEM image obtained at a first e-beam tilt setting of the SEM tool, and a second SEM image obtained at a second e-beam tilt setting of the SEM tool;
generation, using the CNN, of disparity data between the first SEM image and the second SEM image;
combination of the disparity data with the second SEM image to generate a reconstructed image of the first SEM image; and
comparison of the reconstructed image and the first SEM image; and
generate, based on the predicted disparity data, depth information associated with the structure patterned on the substrate.

2 . A non-transitory computer-readable medium comprising instructions stored therein that, when executed by one or more processors, are configured to cause the one or more processors to at least:
obtain a pair of images of a structure of a patterned substrate, the pair of images including a first image captured at a first angle with respect to the patterned substrate, and a second image captured at a second angle different from the first angle; generate, via a model using the first image as input, disparity data between the first image and the second image, the disparity data being indicative of depth information associated with the first image; combine the disparity data with the second image to generate a reconstructed image corresponding to the first image; and adjust, based on a performance function, one or more parameters of the model causing the performance function to be within a specified performance threshold, the performance function being a function of the disparity data, the reconstructed image, and the first image, the model configured to generate data convertible to depth information of a structure of a patterned substrate.

3 . The medium of claim 2 , wherein the disparity data comprises a difference in coordinates of similar features within the first image and the second image.

4 . The medium of claim 2 , wherein the reconstructed image is generated by performance of a composition operation between the disparity data and the second image to generate the reconstructed image.

5 . The medium of claim 2 , wherein the performance function further comprises a loss function computed based on disparity characteristics associated with a pair of stereo images of prior one or more patterned substrates, and the disparity data predicted by the model.

6 . The medium of claim 5 , wherein the disparity characteristics based on the prior one or more patterned substrates comprises disparity expressed as a piecewise smooth function, wherein a derivative of the disparity is piecewise continuous.

7 . The medium of claim 5 , wherein the disparity characteristics based on the prior one or more patterned substrates comprises disparity expressed as piecewise constant.

8 . The medium of claim 5 , wherein the disparity characteristics based on the prior one or more patterned substrates comprises disparity expressed as a function having a jump at edges of a structure within an image, the edges being detected based on a gradient of an intensity profile within the image.

9 . The medium of claim 2 , wherein the instructions configured to adjust the one or more parameters of the model are configured to cause the one or more processors to:
determine the performance function based on the disparity data, and the reconstructed image; determine whether the performance function is within the specified performance threshold; and in response to the performance function not being within the specified performance threshold, adjust the one or more parameters of the model to cause the performance function to be within the specified performance threshold, the adjustment based on a gradient of the performance function with respect to the one or more parameters.

10 . The medium of claim 1 , wherein the first image is a normal image associated with an e-beam directed perpendicular to the patterned substrate, and the second image is associated with an e-beam directed at an angle more 90° or less than 90° with respect to the patterned substrate.

11 . The medium of claim 2 , wherein instructions configured to cause the one or more processors to obtain the pair of images are further configured to cause the one or more processors to obtain a plurality of pairs of SEM images of a patterned substrate, each pair including a first SEM image associated with a first e-beam tilt setting of a metrology tool, and a second SEM image associated with a second e-beam tilt setting of the metrology tool.

12 . The medium of claim 2 , wherein the performance function further comprises another loss function computed as a sum of similarity between an image of a plurality of images and a corresponding reconstructed image.

13 . The medium of claim 1 , wherein the instructions are further configured to cause the one or more processors to obtain, via the metrology tool, a single SEM image of a patterned substrate at the first e-beam tilt setting of the metrology tool.

14 . The medium of claim 13 , wherein the single SEM image is a normal image obtained by directing an e-beam approximately perpendicular to the patterned substrate.

15 . A method comprising:
obtaining a pair of images of a structure of a patterned substrate, the pair of images including a first image captured at a first angle with respect to the patterned substrate, and a second image captured at a second angle different from the first angle; generating, via a model using the first image as input, disparity data between the first image and the second image, the disparity data being indicative of depth information associated with the first image; combining the disparity data with the second image to generate a reconstructed image corresponding to the first image; and adjusting, based on a performance function, one or more parameters of the model causing the performance function to be within a specified performance threshold, the performance function being a function of the disparity data, the reconstructed image, and the first image, the model configured to generate data convertible to depth information of a structure of a patterned substrate.

16 . The method of claim 15 , wherein the disparity data comprises difference in coordinates of similar features within the first image and the second image.

17 . The method of claim 15 , wherein the reconstructed image is generated by performing a composition operation between the disparity data and the second image to generate the reconstructed image.

18 . The method of claim 15 , wherein the performance function further comprises a loss function computed based on disparity characteristics associated with a pair of stereo images of prior one or more patterned substrates, and the disparity data predicted by the model.

19 . The method of claim 18 , wherein the disparity characteristics comprises at least one selected from:
disparity being a piecewise smooth function, wherein a derivative of the disparity is piecewise continuous; dispa

Assignees

• Asml Netherlands Bv

Inventors

• Houben Tim
• Huisman Thomas Jarik
• Pisarenco Maxim
• Middlebrooks Scott Anderson
• Batistakis Chrysostomos
• Cao Yu

Classifications

• G06T2207/20084

  Artificial neural networks [ANN] · CPC title

• G06T2207/20081

  Training; Learning · CPC title

• G06T2207/20212

  Image combination · CPC title

• G06T2207/10012

  Stereo images · CPC title

• G06T2207/30148

  Semiconductor; IC; Wafer · CPC title