Abstract: Systems and methods for generating volumetric data are disclosed. Such systems and methods may include scanning a sample at a plurality of focal planes located along a depth direction of the sample. Such systems and methods may include generating, via a detector of a metrology sub-system, a plurality of images of a volumetric field of view of the sample at the plurality of focal planes. Such systems and methods may include aggregating the plurality of images to generate volumetric data of the volumetric field of view of the sample. The metrology sub-system may include a Linnik interferometer.

Abstract: Methods and systems for training a neural network for defect detection in low resolution images are provided. One system includes an inspection tool that includes high and low resolution imaging subsystems and one or more components that include a high resolution neural network and a low resolution neural network. Computer subsystem(s) of the system are configured for generating a training set of defect images. At least one of the defect images is generated synthetically by the high resolution neural network using an image generated by the high resolution imaging subsystem. The computer subsystem(s) are also configured for training the low resolution neural network using the training set of defect images as input. In addition, the computer subsystem(s) are configured for detecting defects on another specimen by inputting the images generated for the other specimen by the low resolution imaging subsystem into the trained low resolution neural network.

Abstract: Methods and systems for training a neural network for defect detection in low resolution images are provided. One system includes an inspection tool that includes high and low resolution imaging subsystems and one or more components that include a high resolution neural network and a low resolution neural network. Computer subsystem(s) of the system are configured for generating a training set of defect images. At least one of the defect images is generated synthetically by the high resolution neural network using an image generated by the high resolution imaging subsystem. The computer subsystem(s) are also configured for training the low resolution neural network using the training set of defect images as input. In addition, the computer subsystem(s) are configured for detecting defects on another specimen by inputting the images generated for the other specimen by the low resolution imaging subsystem into the trained low resolution neural network.

Abstract: Systems and methods for multi-dimensional metrology and inspection of a specimen such as a bumped wafer are provided. One method includes scanning the specimen with partial oblique illumination to form an image of the structure, either through the normal collection angle or through an oblique collection angle. The method also includes integrating an intensity of the image and determining a height of the structure from the integrated intensity. The integrated intensity may be approximately proportional or inversely proportional to the height of the structure. In addition, the method may include scanning the specimen with bright field illumination to form a bright field image of the specimen. The method may also include determining a lateral dimension of the structure from the bright field image. Furthermore, the method may include detecting defects on the specimen from the bright field image or the obliquely-illuminated image.

Abstract: Systems and methods for assessing a dimension of a feature on a specimen are provided. A system may include an illumination system configured to scan the specimen with light at multiple focal planes substantially simultaneously. The system may also include a collection system that may include multiple collectors. Approximately all light returned from one of the multiple focal planes may be collected by one of the multiple collectors. In addition, the system may include a processor configured to determine a relative intensity of the collected light. The processor may also be configured to assess a dimension of the feature on the specimen in a direction substantially perpendicular to an upper surface of the specimen using the relative intensity.