Method, system and computer program product for producing a subsurface laser engraving

Abstract

A method, and related system and computer program product are provided for producing a subsurface laser engraving (SSLE). The method involves, using at least one processor, generating a three-dimensional (3D) model for the object based on a two-dimensional (2D) digital image file of the object, by applying a trained machine learning (ML) model to the 2D digital image file, generating a point cloud model for the object based at least on the 3D model for the object, and controlling a focal position and a focal depth of a laser, based at least on the point cloud model for the object, while the laser performs subsurface engraving of a transparent material block to produce the SSLE depicting the object.

Description

METHOD, SYSTEM AND COMPUTER PROGRAM PRODUCT FOR PRODUCING A SUBSURFACE LASER ENGRAVINGCROSS-REFERENCE TO RELATED APPLICATION

[0001] This application claims priority to and the benefit of U.S. Provisional Patent Application 63 / 703,117, filed October 3, 2024, and titled “METHOD, SYSTEM AND COMPUTER PROGRAM PRODUCT FOR PRODUCING A SUBSURFACE LASER ENGRAVING”, the contents of which are incorporated herein by reference in their entirety, where permitted.FIELD OF THE DISCLOSURE

[0002] This disclosure relates to methods, systems and computer program products for producing a subsurface laser engraving (SSLE).BACKGROUND OF THE DISCLOSURE

[0003] A subsurface laser engraving (SSLE) (also known as a laser crystal engraving or bubblegram) is a crystal-like transparent material block (e.g., a borosilicate glass block or acrylic block) that is engraved by a pulsed laser diode focused below the surface of the material block to create miniscule localized subsurface fractures that collectively depict an object in three dimensions. SSLEs may be produced as gifts or mementos (e.g., desktop or keychain ornaments, or awards) with the engraved design showing objects such as a portrait of a person, a landscape or cityscape, and / or other graphics and text. The principles for producing SSLEs are described in U.S. patent no. 5,206,496A.

[0004] The object depicted in three dimensions by an SSLE can be based on two- dimensional (2D) images, such as an image of a portrait of a human person. This requires a human artist to interpret the 2D image to manually create a 3D computer model of the object. Software can then be used to convert the 3D model to a point cloud model, which is processed by a computer to control the laser's focal position and focal depth during the engraving process. Verisimilitude between the portrait depicted in the image and the portrait depicted by the SSLE will depend on the skill, style and subjective interpretation of the artist who created the 3D model. Minor differences inthese factors can result in different depictions of facial features (especially nasal features and eye sockets) and eye gaze point, which affect the accuracy and aesthetic appeal of the object depicted by the SSLE. The need for skilled artists increases production costs. Even skilled artists can take an hour or longer to create a 3D model, which can be the rate-limiting step in producing SSLEs. Accordingly, at present, SSLEs produced based on 2D images are typically ordered days before delivery.

[0005] There remains a need in the art for rapidly producing SSLEs based on 2D images of objects to meet point-of-order delivery and volume demands at tourist venues, impulse purchase environments (e.g., fairgrounds and amusement parks), or special events (e.g., weddings), with reliable verisimilitude between the object depicted by the 2D image and by the SSLE, and without the involvement of skilled artists.SUMMARY OF THE DISCLOSURE

[0006] In one aspect, the present disclosure comprises a method for producing a subsurface laser engraving (SSLE) depicting an object. The method comprises: using at least one processor, generating a three-dimensional (3D) model for the object based on a two-dimensional (2D) digital image file of the object, wherein the generating comprises applying a machine learning (ML) model to the 2D digital image file, and wherein the ML model is trained using a training dataset comprising training input 2D digital image files and respective training output 3D models, wherein each training input 2D digital image file and the respective training output 3D model depicts a respective training object; using the at least one processor, generating a point cloud model for the object based at least on the 3D model for the object; and using the at least one processor, controlling a focal position and a focal depth of a laser, based at least on the point cloud model for the object, while the laser performs subsurface engraving of a transparent material block to produce the SSLE depicting the object.

[0007] In another aspect, the present disclosure comprises a system for producing a subsurface laser engraving (SSLE) depicting an object, for use with a laser device comprising a laser diode for generating a laser having a focal position and a focal depth that are controllable. The system comprises at least one processor operatively connected to the laser device and operatively connected to at least one memory comprising at least one non-transitory computer readable medium storing instructions executable by at least one processor to implement a method comprising: generating athree-dimensional (3D) model for the object based on a two-dimensional (2D) digital image file of the object, wherein the generating comprises applying a machine learning (ML) model to the 2D digital image file, and wherein the ML model is trained using a training dataset comprising training input 2D digital image files and respective training output 3D models, wherein each training input 2D digital image file and the respective training output 3D model depicts a respective training object; generating a point cloud model for the object based at least on the 3D model for the object; and controlling the focal position and the focal depth of the laser, based at least on the point cloud model for the object, while the laser performs subsurface engraving of a transparent material block to produce the SSLE depicting the object.

[0008] In another aspect, the present disclosure comprises a computer program product for producing a subsurface laser engraving (SSLE) depicting an object. The computer program product comprises at least one non-transitory computer readable medium storing instructions executable by at least one processor operatively connected to a laser device comprising a laser diode for generating a laser having a focal position and a focal depth that are controllable by the at least one processor, to implement a method. The method comprises: generating a three-dimensional (3D) model for the object based on a two-dimensional (2D) digital image file of the object, wherein the generating comprises applying a machine learning (ML) model to the 2D digital image file, and wherein the ML model is trained using a training dataset comprising training input 2D digital image files and respective training output 3D models, wherein each training input 2D digital image file and the respective training output 3D model depicts a respective training object; generating a point cloud model for the object based at least on the 3D model for the object; and controlling the focal position and the focal depth of the laser, based at least on the point cloud model for the object, while the laser performs subsurface engraving of a transparent material block to produce the SSLE depicting the object.

[0009] Embodiments of the method, system and the computer program product as described above may be further characterized by one or a combination of further features as subsequently described herein.

[0010] In embodiments of the method, the system and the computer program product, the method may comprise, using the at least one processor, causing a display device to display at least one interface configured to permit a user to select the 2Ddigital image file to be used for the generating of the 3D model of the object by selecting the 2D digital image file from a plurality of stored 2D digital images or by activating a digital camera to generate the 2D digital image file. The generating of the 3D model may be based on the 2D digital image file that is selected by the user using the at least interface. The system may comprise a kiosk comprising the display device and the laser device.

[0011] In embodiments of the method, the system and the computer program product, the method may comprise, using the at least one processor, causing a display device to display at least one interface configured to permit a user to specify a position of the 2D digital image file relative to a template of the transparent material block to be engraved to produce the SSLE. The controlling of the focal position of the laser, while the laser performs the subsurface engraving of the transparent material block to produce the SSLE comprising the depiction of the object, may be further based on the position of the 2D digital image file relative to the template that is specified by the user using the at least one interface. The system may comprise a kiosk comprising the display device and the laser device.

[0012] In embodiments of the method, the system and the computer program product, the method may comprise receiving an indication that the 3D model for the object that was generated is satisfactory. The step of generating the point cloud model for the object based at least on the 3D model for the object may be conditional on receiving the indication that the 3D model is satisfactory.

[0013] In embodiments of the method and the system, the at least one processor may comprise a processor of at least one server computer located remotely from the laser device. The processor of the at least one server computer may perform at least the step of generating the 3D model for the object based on the 2D digital image file of the object.

[0014] In embodiments of the method, the system and the computer program product, the SSLE to be produced may be one of a plurality of SSLEs to be produced by engraving a plurality of transparent material blocks, wherein a respective location on an engraving table of the laser device is assigned to each of the plurality of the transparent material blocks and stored in a memory. The step of controlling of the focal position of the laser, while the laser performs the subsurface engraving of the transparent material block to produce the SSLE comprising the depiction of the object,may be further based at least on the respective location on the engraving table of the laser device that is stored and assigned to the transparent material block.

[0015] Each of the features described above as features of particular embodiments may also exist independently of applying the ML model to the 2D digital file to generating the 3D model. That is, in some embodiments, the application of the ML model to generate the 3D model may, in embodiments, be omitted or considered optional.BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The foregoing and other aspects of the disclosure will be better appreciated with reference to the attached drawings, in which like reference characters denote like parts, as follows.

[0017] Figure 1 is a schematic depiction of an embodiment of a system of the present disclosure for producing an SSLE.

[0018] Figure 2 is a functional block diagram of a system of Figure 1 .

[0019] Figure 3 is a flow chart showing an embodiment of a method of the present disclosure for producing an SSLE, which is implemented by the system of Figure 1.

[0020] Figure 4 shows a display screen of a consumer computer showing a graphical user interface for selecting a 2D digital image file and submitting an order for an SSLE.

[0021] Figure 5 is a schematic depiction of applying a machine learning model to a 2D digital image file depicting an object to generate a 3D model of the object.

[0022] Figure 6 is a schematic depiction of a training dataset of training input 2D digital image files depicting objects and respective training output 3D models of the objects.

[0023] Figure 7 is a flow chart showing an embodiment of a method of training the machine model for generating 3D models.

[0024] Figure 8 shows a display screen of a laser control computer showing a graphical user interface for submitting an indication of whether a 3D model for an object is satisfactory.

[0025] Figure 9 is a schematic depiction of generating a point cloud model of an object based on a 3D model of the object.

[0026] Figure 10 shows a display screen of a laser control computer showing a graphical user interface for tracking a queue of SSLEs to be produced.

[0027] Figure 11 shows multiple transparent material blocks ready to be engraved by a laser diode to produce multiple SSLEs.

[0028] Figure 12 shows a kiosk implementing aspects of an embodiment of a system of the present disclosure for producing an SSLE.DETAILED DESCRIPTION OF EXAMPLE EMBODIMENTS

[0029] INTERPRETATION

[0030] For simplicity and clarity of illustration, where considered appropriate, reference numerals may be repeated among the Figures to indicate corresponding or analogous elements. In addition, numerous specific details are set forth in order to provide a thorough understanding of the embodiment or embodiments described herein. However, it will be understood by those of ordinary skill in the art that the embodiments described herein may be practiced without these specific details. In other instances, well-known methods, procedures and components have not been described in detail so as not to obscure the embodiments described herein. It should be understood at the outset that, although exemplary embodiments are illustrated in the figures and described below, the principles of the present disclosure may be implemented using any number of techniques, whether currently known or not. The present disclosure should in no way be limited to the exemplary implementations and techniques illustrated in the drawings and described below.

[0031] Unless otherwise explained, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs.

[0032] Various terms used throughout the present description may be read and understood as follows, unless the context indicates otherwise: "or" as used throughout is inclusive, as though written "and / or"; singular articles and pronouns as used throughout include their plural forms, and vice versa; similarly, gendered pronouns include their counterpart pronouns so that pronouns should not be understood as limiting anything described herein to use, implementation, performance, etc. by a single gender; "exemplary" should be understood as "illustrative" or "exemplifying" and not necessarily as "preferred" over other embodiments. Further definitions for termsmay be set out herein; these may apply to prior and subsequent instances of those terms, as will be understood from a reading of the present description. It will also be noted that the use of the term "a" or "an" will be understood to denote "at least one" in all instances unless explicitly stated otherwise or unless it would be understood to be obvious that it must mean "one". The phrase "at least one of" is understood to be one or more. The phrase "at least one of... and..." is understood to mean at least one of the elements listed or a combination thereof, if not explicitly listed. For example, "at least one of A, B, and C" is understood to mean A alone or B alone or C alone or a combination of A and B or a combination of A and C or a combination of B and C or a combination of A, B, and C.

[0033] The term "comprising" and its derivatives, as used herein, are intended to be open ended terms that specify the presence of the stated features, elements, components, groups, integers, and / or steps, but do not exclude the presence of other unstated features, elements, components, groups, integers and / or steps. The foregoing also applies to words having similar meanings such as the terms, "including", "having" and their derivatives. It will be understood that any embodiments described as "comprising" certain components may also "consist of" or "consist essentially of" these components, wherein "consisting of" has a closed-ended or restrictive meaning and "consisting essentially of" means including the components specified but excluding other components except for components added for a purpose other than achieving the technical effects described herein.

[0034] It will be understood that any component defined herein as being included may be explicitly excluded from the claimed invention by way of proviso or negative limitation, such as any specific components or method steps, whether implicitly or explicitly defined herein.

[0035] In addition, all ranges given herein include the end of the ranges and also any intermediate range points, whether explicitly stated or not.

[0036] Terms of degree such as "substantially", "about" and "approximately" as used herein mean a reasonable amount of deviation of the modified term such that the end result is not significantly changed. These terms of degree should be construed as including a deviation of at least ±5% of the modified term if this deviation would not negate the meaning of the word it modifies.

[0037] The abbreviation, "e.g." is derived from the Latin exempli gratia, and is used herein to indicate a non-limiting example. Thus, the abbreviation "e.g." is synonymous with the term "for example." The word "or" is intended to include "and" unless the context clearly indicates otherwise.

[0038] Modifications, additions, or omissions may be made to the systems, apparatuses, and methods described herein without departing from the scope of the disclosure. For example, the components of the systems and apparatuses may be integrated or separated. Moreover, the operations of the systems and apparatuses disclosed herein may be performed by more, fewer, or other components and the methods described may include more, fewer, or other steps. Additionally, steps may be performed in any suitable order. As used in this document, "each" refers to each member of a set or each member of a subset of a set.

[0039] "Attached", as used herein, in describing the relationship between two connected parts includes the case in which the two connected parts are "directly attached" with the two connected parts being in contact with each other, and the case in which the connected parts are "indirectly attached" and not in contact with each other, but connected by one or more intervening other part(s) between.

[0040] The embodiments of the disclosures described herein are exemplary (e.g., in terms of materials, shapes, dimensions, and constructional details) and do not limit by the claims appended hereto and any amendments made thereto. Persons skilled in the art will appreciate that there are yet more alternative implementations and modifications possible, and that the following examples are only illustrations of one or more implementations. The scope of the invention, therefore, is only to be limited by the claims appended hereto and any amendments made thereto.

[0041] COMPUTER IMPLEMENTATION

[0042] "Memory", as used herein, refers to a non-transitory tangible computer- readable medium for storing information (e.g., data or data structures) in a format readable by a processor, and / or instructions (e.g., computer code or software programs or modules) that are readable and executable by a processor to implement an algorithm. The term "memory" includes a single device or a plurality of physically discrete, operatively connected devices despite use of the term in the singular. Nonlimiting types of memory include solid-state semiconductor, optical, magnetic, and magneto-optical computer readable media. Examples of memory technologies includeoptical discs such as compact discs (CD-ROMs) and digital versatile (or video) discs (DVDs), magnetic media such as floppy disks, magnetic tapes or cassettes, and solid state semiconductor random access memory (RAM) devices, read-only memory (ROM) devices, electrically erasable programmable read-only memory (EEPROM) devices, flash memory devices, memory chips and combinations of the foregoing. Memory may be non-volatile or volatile. Memory may be physically attached to a processor, or remote from a processor. Memory may be removable or non-removable from a system including a processor. Memory may be operatively connected to a processor in such a way as to be accessible by a processor. Instructions stored by a memory may be based on a plurality of programming and / or markup languages known in the art, with non-limiting examples including the C, C++, C#, Python ™, MATLAB ™, Java ™, JavaScript ™, Perl ™, PHP ™, SQL ™, Visual Basic ™, Hypertext Markup Language (HTML), Extensible Markup Language (XML), and combinations of the foregoing programming languages. Instructions stored by a memory may also be implemented by configuration settings for a fixed-function device, gate array or programmable logic device.

[0043] "Processor", as used herein, refers to one or more electronic hardware devices that is / are capable of reading and executing instructions stored on a memory to perform operations on data, which may be stored on a memory or provided in a data signal. The term "processor" includes a single device or a plurality of physically discrete, operatively connected devices despite use of the term in the singular. The plurality of processors may be arrayed or distributed. Non-limiting examples of processors include integrated circuit semiconductor devices and / or processing circuit devices referred to as computers, servers or terminals having single or multi-processor architectures, microprocessors, microcontrollers, microcontroller units (MCU), central processing units (CPU), field-programmable gate arrays (FPGA), application specific circuits (ASIC), digital signal processors, and combinations of the foregoing.

[0044] Any method, application or module herein described may be implemented using computer readable / executable instructions that may be stored or otherwise held by a memory and executed by a processor. Aspects of the present disclosure may be described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the disclosure. It will be understood that each block of the flowchart illustrations and / orblock diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor, such that the processor, and a memory storing the instructions, which execute via the processor, collectively constitute a machine for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0045] The flowcharts and functional block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and / or flowchart illustration, and combinations of blocks in the block diagrams and / or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

[0046] ADDITIONAL TERMINOLOGY

[0047] "Subsurface laser engraving" or "SSLE", as used herein, refers to a transparent material block (e.g., a borosilicate glass block or acrylic block) that is engraved by a laser diode to create miniscule localized sub-surface fractures that collectively depict an object in three-dimensions (3D). The transparent material block may also be referred to as a crystal.

[0048] "3D model", as used herein, refers to a set of data representing a surface of an object in a three-dimensional coordinate system. A 3D model may represented in a number of formats as known in the art.

[0049] "Point cloud model", as used herein, refers to a set of data representing a geometric location of a set of discrete points in in a three-dimensional coordinatesystem. The set of discrete points of the point cloud model may collectively represent a surface of an object.

[0050] "Machine learning model" or "ML model", as used herein, refers to a computational model having at least some parameters (e.g., weights, biases, classifications, analyses) that are tunable and defined by machine learning. "Machine learning" refers to an automated and repeated process where a computational model is applied to a training set of input data to generate a set of actual output data, and values and / or interrelationships of one or more parameters of the computational model are determined or updated automatically (i.e. , without being actively programmed by a human user) in accordance with a training algorithm so that the actual output data more closely approaches or resembles a training set of output data associated with the training set of input data and determined independently of the machine learning model. Machine learning may use models such as artificial neural networks, regression models, decision trees, support vector machines, Bayesian networks, random forest learning, dimensionality reduction algorithms, and boosting algorithms, as known in the art, may use genetic algorithms, and may use supervised learning (i.e., using human-labeled data of the training set) or unsupervised learning (i.e., using unlabeled data of the training set).

[0051] SYSTEM FOR PRODUCING AN SSLE

[0052] Figure 1 shows an embodiment of a system 2 for producing an SSLE. Figure 2 shows a functional block diagram of the system of Figure 1. In the embodiment shown in Figure 1 , the system 2 includes a server computer 4, and a laser control computer 6 operatively connected to a laser device 8. In embodiments, the system 2 may further be considered as including a customer computer 10. In Figures 1 and 2, the dashed lines between the computers of system 2 indicate operative communication connections between the components, which may comprise wired and / or wireless connections, such as may be implemented by one or more data buses and / or one or more communications networks (e.g., the Internet and / or a local area network); it will be understood that the computers of system 2 are equipped with communications means (e.g., cellular, Wi-Fi and / or Ethernet modems, and data bus ports, etc.) as known in the art to enable such communications.

[0053] Figure 1 shows a server computer 4 operatively connected to a single laser control computer 6 that is operatively connected to a single laser device 8, andoperatively connected to a single customer computer 10. In embodiments, the server computer 4 may comprise a plurality of networked computers as subsequently described. In other embodiments, the server computer 4 may be operatively connected to additional laser control computers 6, each of which may be operatively connected to one or more laser devices 8, and the server computer 4 may be operatively connected to additional customer computers 10 in a many-to-one server-to-client relationship.

[0054] In the embodiment of Figure 1 , the server computer 4, the laser control computers and the customer computer 10 are shown as physically discrete computers under the control of different users (as subsequently described) and which may be located remotely from one another. In other embodiments, one or more of the server computer 4, the laser control computer 6, and the customer computer 10 may be physically integrated with each other. For example, in one embodiment, the server computer 4, the laser control computer 6 and the customer computer 10, may be physically integrated in a kiosk and under control of a single user. Accordingly, the terms "server", "laser control", and "customer" are used to functionally distinguish between computers shown in the embodiment of Figure 1 , but do not limit the computers in practice to particular users.

[0055] In the embodiment shown in Figures 1 and 2, the user 12 of the server computer 4 may be an administrator of the system 2, such as a software-as-a-service (SaaS) provider. In the embodiment shown in Figures 1 and 2, the server computer 4 comprises a processor 20 and a memory 22 (Figure 2). In the embodiment shown in Figure 1 , the server computer 4 comprises a server workstation 4a, operatively connected via the Internet to a plurality of worker computers 4b, 4c, in a computer cluster. The worker computers 4b, 4c may be general purpose computers with graphics processing units (GPUs). (Figure 1 shows two worker computer 4b, 4c, but there may be a greater number of worker computers, and they may be operatively connected by means other than the Internet, such as a local area network.) The roles of the server workstation 4a and worker computers 4b, 4c are subsequently described with respect to step 54 of the method 50 shown in Figure 3. In other embodiments the server computer 4 may be implemented by a single computing device having a processor and a memory.

[0056] In the embodiment shown in Figure 1 , the user 14 of the laser control computer 6 may be a vendor of SSLEs that subscribes to a software service provided by the user 12 of the server computer 4. In the embodiment shown in Figure 1 , the laser control computer 6 is a desktop computer or laptop computer (e.g., computers that operate using the Microsoft Windows (TM) operating system (Microsoft Corporation) or the macOS (TM) operating system (Apple Inc.)) comprising a processor 28 and a memory 30 (Figure 2). In other embodiments, the laser control computers may be implemented by other computer devices, such as a smartphone or tablet computer or hardware and software (e.g., firmware) forming part of the laser device 8.

[0057] In the embodiment shown in Figures 1 and 2, the laser device 8 is implemented as a standalone device. The laser device 8 includes a laser diode 31 capable of sub-surface engraving of a transparent material block 18 to produce an SSLE. Referring to Figure 2, it will be understood that the processor 28 of the laser control computer 6 is capable of controlling an actuator 32 (e.g., a motorized mechanism that translates and / or pivots the laser diode 31 ) for adjusting a focal position (e.g., a horizontal position) of a laser produced by the laser diode 31 , and an actuator 34 (e.g., a motorized mechanism that adjusts a position, and hence a focal length, of a lens for the laser diode 31 , or other mechanism) for adjusting a focal depth (e.g., a vertical location) of the laser produced by the laser diode 31 . Accordingly, the laser diode 31 can be controlled to engrave different locations of the transparent material block 18 at different subsurface depths to produce an SSLE. Laser devices suitable for use in the system 2 are known in the art. Non-limiting examples include the 3DLaserBox Jet (TM) model laser device (Crystallize It! Inc.; Richmond Hill, Canada).

[0058] In the embodiment shown in Figure 1 , the user 16 of the customer computer 10 may be a customer who wishes to have an SSLE produced. In the embodiment shown in Figures 1 and 2, the customer computer 10 may be a mobile computing device commonly known as a smartphone such as those that operate using the iOS (TM) mobile operating system (Apple Inc.) or the Android (TM) mobile operating system (Google LLC). Referring to Figure 2, the smartphone comprises a processor 36, a memory 38, a touchscreen 40, and digital camera 42. In other embodiments, the customer computer6 may be implemented by other computer devices, such as a tablet computer, a desktop computer, a laptop computer, or other hardware and software.

[0059] Referring to Figure 2, in embodiments, the server computer 4 may be used as an application server by having its memory 20 store part or all of the instructions 26 for producing SSLEs as subsequently described. In embodiments, the laser control computer 6 may have its memory 30 store part or all of the instructions 26 for producing SSLEs as subsequently described. In embodiments, the customer computer 10 may have its memory 38 store part or all of the instructions 39 for producing SSLEs as subsequently described. The instructions 26 and / or 39 are executable by the processor 20 of the server computer 4 and / or the processor 28 of the laser control computer 6 and / or the processor 36 of the customer computer 10 to implement a method for producing SSLEs as subsequently described, and may be considered as a computer program product of the present disclosure.

[0060] As previously described, the system may be implemented in a kiosk 11 such as shown in one embodiment in Figure 12. In Figure 12, the dashed lines between the components indicate operative communication connections between the components, which may comprise wired and / or wireless connections, such as may be implemented by one or more data buses and / or one or more communications networks. The kiosk 11 includes the laser control computer 6 and the customer computer 10, which are operatively connected to a laser device 8, a display device which may be in the form of a touchscreen 40 for use by the user 16, and a digital camera 42 positioned to acquire a 2D digital image 70 of the user 16. The server computer 4 and its constituent processor may located remotely from the kiosk 11 and in wireless communication with the laser control computer 6 and the customer computer 10. This processors of this embodiment of the system may similarly execute stored instructions to implement a method for producing SSLEs as subsequently described.

[0061] METHOD FOR PRODUCING AN SSLE

[0062] An embodiment of the method 50 for producing an SSLE is described below with reference to the flow chart shown in Figure 3, and with reference to accompanying Figures 4 to 11. In this embodiment, the method 50 is performed using the system 2 shown in Figure 1 in which the server computer 4, laser control computer 6 and the consumer computer 10 are discrete computers. As noted, however, one or more of these computers may be physically integrated with each other, or interconnected for distributed computing, with one non-limiting example being shown by the embodiment of the system shown in Figure 12. Accordingly, reference to the steps of the method50 being executed by a processor or at least one processor may include performance of the steps being performed by the processor(s) of one or more of the server computer 4, laser control computer 6 and / or the consumer computer 10 executing instructions 26 stored on the memory 22, 30, 38 of one or more of the server computer 4, laser control computer s and the consumer computer 10, respectively.

[0063] At step 52 of the method 50 (Figure 3), and referring to Figure 4, the touchscreen 40 of the consumer computer 10 displays an interface for selecting a 2D digital image 70 depicting an object and submitting an orderfor an SSLE. The interface may be implemented by a webpage on an internet browser application or an interface of a dedicated software application. In this example, the object depicted by the 2D digital image 70 is a portrait photograph of a person. In one embodiment, the 2D digital image 70 may be selected from a gallery of digital image files stored in the memory 38 of the consumer computer 10, or another memory (e.g., an online archive of digital image files) accessible to the consumer computer 10. In another embodiment, the 2D digital image 70 may be selected by activating the digital camera 42 (Figure 2) of the consumer computer 10 and using the digital camera 42 to take a photograph to generate a digital image file. In the embodiment shown in Figure 4, the interface also displays a 2D template 72 representing the boundary of a transparent material block to be engraved to produce the SSLE. The interface may allow for selection of the template in terms of size and shape (e.g., a trapezoidal prismatic shape as shown) from a database of templates having different sizes and shapes (e.g., rectangular prismatic, heart shaped, irregular, etc.). In embodiments, the interface allows the user 16 of the consumer computer 10 to position, rotate, crop, scale and performing other editing of the 2D digital image 70 (e.g., by using touch, drag, and pinch gestures on the touchscreen 40 of the consumer computer 10) relative to the template 72 to specify how the object will appear (e.g., in terms of position, orientation, extent of the 2D digital image, size of the 2D digital image) on the transparent material block to be engraved of the SSLE to be produced. The interface may also allow the user 16 of the consumer computer 10 to input information for ordering an SSLE such as the name, address, and billing information of the user 16 and / or a recipient of the SSLE. In the embodiment shown in Figure 4, the interface includes a virtual button 76 labelled "Submit Order", which when touched by the user 16, causes transmission to the server computer 4 of a 2D digital image file for the 2D digital image 70, as well as coordinate informationindicative of the position and scale of the 2D digital image 70 relative to the selected 2D template 72, the selected 2D template 72, and other information for completing the order.

[0064] At step 54 of the method 50 (Figure 3), the server computer 4 generates a 3D model for the object by applying a machine learning model to the 2D digital image file storing the digital image 70. Figure 5 is a schematic depiction of applying a machine learning model to a 2D digital image 70 depicting an object to generate a 3D model 78 of the object. (In Figure 5, the front surface of the 3D model 78 appears somewhat flat but in actuality it may be non-flat to reflect contours of facial features depicted by the 2D digital image file.) As a non-limiting example, the 2D digital image file may in a known file format such as the JPEG (Joint Photographic Experts Group) file format. As a non-limiting example, the 3D model 78 may be stored in a known file format such as a OBJ file format (Wavefront Technologies) that represents the object in 3D as a polyhedron defined by data including coordinates of vertices of the polyhedron, faces of the polyhedron defined by subsets of the vertices, and texture mapping of the 2D digital image 70 to the 3D model 78.

[0065] The machine learning model may generate the 3D model 78 for the object within a matter of seconds or a few minutes, depending on the computation power of the processor 20 of the server computer 4 and the feature complexity of the 2D digital image 70. This allows for a substantial time saving from the conventional approach of using human artists to manually create the 3D model. Further, the use of the machine learning model to generate 3D models 66 may allow for greater uniformity in quality than is possible with different human artists.

[0066] In the embodiment shown in Figure 1 , the server computer 4 comprises a server workstation 4a operatively connected to worker computers 4b, 4c by the Internet. The server work station 4a may receive a request to convert the 2D digital image 70 to a 3D model 78, as a result of the user 16 of the consumer computer 10 selecting the virtual button 76 labelled "Submit Order" (Figure 4) as previously described. In response to receiving the request, the server workstation 4a creates a "conversion job" for the worker computers 4b, 4c to convert the 2D digital image 70 to the 3D model 78. When either of the worker computers 4b, 4c deem themselves to have sufficient available processing power, the worker computer 4b and / or 4c will contact the server workstation 4a via the Internet. When the server workstation 4a is contacted by one ofthe worker computers 4b, 4c and a conversion job is available, then the worker computer4b or 4c claims the conversion job (i.e. , provides an indication that the worker computer 4b or 4c will process the conversion job), downloads the required assets for the conversion job (e.g., the 2D digital image file for the 2D digital image 70, and coordinate information indicative of the position and scale of the 2D digital image 70 relative to the selected 2D template 72), applies the machine learning model to the 2D digital image 70 to complete the conversion job to produce the 3D model 78, and sends the 3D model 78 to the server workstation 4a. The use of the server workstation 4a and worker computers 4b, 4c in this manner allows the system 2 to be conveniently scaled for simultaneous processing of multiple conversion jobs, limited only by the number of worker computers 4b, 4c and the processing power of their GPUs.

[0067] In the embodiment shown in Figure 5, the machine learning model automatically positions and / or creates the 3D model so that it is positioned within a 3D template 80 representing the 3D boundary of a transparent material block to be engraved to produce the SSLE. The 3D template 80 corresponds to the geometry of the 2D template 72, but is further defined by one or more depth dimensions. This positioning is based at least partly on the coordinate information regarding the position and scale of the 2D digital image 70 relative to the 2D template 72 that was transmitted from the consumer computer 10 to the server computer 4.

[0068] The machine learning model employs algorithms for converting the 2D digital image file to a 3D model. Such algorithms are known in the art and do not by themselves constitute the present invention. In embodiments, algorithms for converting the 2D digital image to a 3D model may use techniques of single-image depth estimation (SIDE) (also known as monocular depth estimation), as known in the art of computer vision. Briefly, SIDE may be used to convert 2D digital images to depth maps by assigning depth values to each pixel or subgroups of pixels of a 2D digital image based on factors such as pixel values (e.g., red-blue-green RGB intensity values), and / or recognition of patterns, shapes and / or textures in the 2D digital image. SIDE techniques may themselves rely on machine learning models such as convolutional neural networks (CNN). As a non-limiting example, such algorithms may be in accordance with principles described in C. Godard et al., "Digging Into Self-Supervised Monocular Depth Estimation", arXiv: 1806.01260 [cs.CV], 17 August 2019, the contents of which is incorporated by reference herein where permitted.

[0069] The machine learning model is trained using a training dataset of training input 2D digital image files and respective training output 3D models, each of which depict a training object, such as a portrait of a person. Figure 6 is a schematic depiction of a training dataset of training input 2D digital image files 70a, 70b,..70i,...70n depicting objects in the form of portraits of people and respective training output 3D models 78a, 78b,..78i,...78n of the portraits. The index 'n' indicates the quantity of 2D digital image files and 3D models in the training dataset, and the index 'i' indicates the generic case. As non-limiting examples, the value of 'n' may be in the hundreds, thousands, tens of thousands or more. It will be understood that the portraits depicted in training input 2D digital image files 70a, 70b,..70i,...70n are different, and accordingly the training output 3D models 78a, 78b,..78i,...78n are different. It will be understood that the 'i'-th training output 3D model 78i, is respective to the training input 2D digital files 70i in the sense that the training output 3D model 78i depicts the same object as the object depicted by the 'i'-th training input 2D digital image file 70i, but in three dimensions.

[0070] Figure 7 is a flow chart showing an embodiment a general method 90 of training the machine model for generating 3D models. At step 92 of the method 90, a training dataset of training input 2D digital image files 70a, 70b,..70i,...70n and training output 3D models 78a, 78b,..78i,...78n is acquired and prepared. The training output 3D models 78a, 78b,..78i,...78n are produced by means other than applying the machine learning model to the training input 2D digital image files 70a, 70b,..70i,...70n. In one embodiment, the training output 3D models 78a, 78b,..78i,...78n are manually produced by skilled artists. In embodiments, the training dataset is such that it includes training output 3D models 78a, 78b,..78i,...78n that have been human-vetted as being of satisfactory quality, while in other embodiments, the training output 3D models 78a, 78b,..78i,...78n may be human-labeled to indicate whether they of satisfactory quality (e.g., "Pass") or unsatisfactory quality (e.g., "Fail"). At step 94 of the method 90, the machine learning model is trained according to a training algorithm, using the training dataset, to determine or update values and / or interrelationships of one or more parameters of the machine learning model in accordance with a training algorithm so that 3D models generated by applying the machine learning model to the training input 2D digital image files 70a, 70b,..70i,...70n more closely resemble the training output 3D models 78a, 78b,..78i,...78n. A variety of training algorithms (e.g., algorithms basedon regression, decision trees, classification, artificial neural networks, clustering, etc.) are known in the art and may be employed in this step. At step 96 of the method 90, the machine learning model is evaluated using a validation dataset 76. The validation dataset may include input 2D digital image files and respective output 3D models in a manner similar to the training dataset, but mutually exclusive of the training dataset. As a non-limiting example, the machine learning model may be evaluated by a human determining whetherthe 3D models generated by applying the machine learning model to the 2D digital image files of the validation dataset appear sufficiently similar to the output 3D models of the validation dataset. As another non-limiting example, the machine learning model may be evaluated by a processor comparing the generated 3D models to the output 3D models of the validation dataset to determine a quantitative degree of similarity. If the evaluation is unsatisfactory, then the method 90 returns to step 94. If the evaluation is satisfactory, then the method 90 proceeds to step 98 of deploying the machine learning model. As the machine learning model is employed, input 2D digital image files for the machine learning model and output 3D models of the machine learning model may be used to augment the training dataset, as subsequently described.

[0071] Referring to Figure 3, at optional step 56 of the method 50, the server computer 4 receives an indicator of whether the 3D model 78 for the object generated by the machine learning model is satisfactory (pass) or unsatisfactory (fail). (If step 56 is omitted, then the method 50 may proceed directly from step 54 to step 58.) Referring to Figure 8, a display screen of the laser control computer 6 shows a graphical user interface for the user 14 to submit an indicator of whether the 3D model 68 for an object is satisfactory. The interface may be implemented by a webpage on an internet browser application or an interface of a dedicated software application, which accesses the data describing the 3D model 78 and the 3D template 80 to be engraved, and renders them on the display screen of the laser control computer 6. The interface may allow the user 14 of the laser control computer 6 to manipulate (e.g., pan, zoom, rotate) the rendered 3D model 78 and the 3D template 80 to inspect them from different viewpoints and scales for accuracy and aesthetic appeal. In the embodiment shown in Figure 8, the interface includes virtual buttons 102, 104 labelled "Pass" and "Fail" respectively, which when selected, causes transmission to the server computer 4 of an indicator that the 3D model 78 is satisfactory or unsatisfactory, respectively.Referring to Figure 3, if the server computer 4 receives a "Fail" indicator, then the method 50 may return to step 54 to regenerate the 3D model (e.g., using a different or modified machine learning model) or the method 50 may be terminated. Conversely, if the server computer 4 receives a "Pass" indicator, then the method 50 may proceed to step 58. If the server computer 4 receives a "Pass" indicator, then the 2D digital image 70 and the generated 3D model 78 may be added to the training dataset to be used for additional training of the machine learning model.

[0072] Referring to Figure 3, at step 58 of the method 50, a file containing data for the 3D model 78 for the object and the template 80 is transmitted to the laser control computer s. In embodiments, the transmission of the 3D model 78 to the laser control computer 6 may occur automatically, in response to the user 14 of the laser control computer s selecting the virtual button 102 labelled "Pass" in Figure 8.

[0073] Referring to Figure 4, at step 60 of the method 50, the laser control computer 6 generates a point cloud model 106 for the object based at least on the 3D model 78 for the object. In embodiments, the point spacings (i.e. the spacing between discrete points of the point cloud model) may be based on size of the 3D template 80 (e.g., a smaller template 80 may be associated with a point cloud model having smaller point spacings). Figure 9 is a schematic depiction of point cloud conversion software running on the laser control computer 6 for generating a point cloud model 106 of an object based on a 3D model 78 of the object. In embodiments, the generation of the point cloud model 106 may occur automatically according to a computer program script that detects receipt of the file containing data for the 3D model.

[0074] Point cloud conversion software for converting the 3D model 78 to a point cloud model 106 is known in the art and does not by itself form part of the present invention. Non-limiting examples include the Cockpit3D (TM) software program (Crystallize It! Inc.; Richmond Hill, Canada). In a non-limiting example, the conversion of the 3D model 78 to the point cloud model 106 may involve the following process. The laser control computer 6 accesses the 3D model 78 such as in the form of an OBJ file defining the object as a polyhedron with the 2D digital image 70 serving as the mapped texture. The file containing the 3D model 78 may have a header section storing information that defines the 3D template 80 for the transparent material block 18 and coordinate information that indicates of the position and scale of the 3D model 80 relative to the 3D template 80. The laser control computer 6 may automaticallydetermine settings for generating the point cloud model 106 such as the number of layers of the point cloud model 106, and the point spacings for the point cloud model 106. These settings may be pre-defined based on the dimensions and geometry of 3D template 80. The laser control computer 6 may convert the 3D model 78 into a grayscale model, and then determine points of the point cloud model 106 based on the grayscale model. For example, in regions where the grayscale model has a higher intensity of pixel values (i.e., the pixels are closer to white values than black values), the laser control computer 6 may define the point cloud model 106 to have a higher density of points to be engraved, which will appear as a corresponding lighter region of the SSLE. The laser control computer 6 saves the point cloud model 106 in a format that is readable by the laser device 8. The positional coordinates (e.g., x, y, and z coordinates) of each point of the point cloud model 106 are used control the focal position and focal depth of the laser diode 31 when engraving the transparent material block 18.

[0075] The size of a file containing data for the point cloud model 106 may be larger than the size of a file containing data for the 3D model 78. Accordingly, generating the point cloud model 106 at the laser control computer 6 may be advantageous in limiting the required bandwidth of data transmission from the server computer 4 to the laser control computer 6. In other embodiments, however, the server computer 4 may generate the point cloud model 106 and transmit a file containing data for the point cloud model 106 to the laser control computer 6, without having to transmit a file containing data for the 3D model 78 to the laser control computer 6.

[0076] In embodiments, after generating of the point cloud model 106, a computer program script may cause the display screen of the laser control computer 6 to display a visual prompt to user 14 of the laser control computer 6. The visual prompt may notify the user 14 that the a SSLE is waiting to be produced, and that a transparent material block having a size and shape corresponding to the 3D template 80 should be placed onto an engraving table of the laser device 8. The computer program script may also cause the display screen of the laser control computer 6 to display an interface for the user 14 of the laser control computer 6 to activate the laser device 8 to start the engraving process.

[0077] Referring to Figure 3, at step 62 of the method 50, the laser control computer 6 controls the focal position and focal depth of a laser generated by the laser device 8based at least on the point cloud model 106 for the object while the laser performs subsurface engraving of a transparent material block 18. The control of the focal position and focal depth may also be based factors such as the specified position of the 2D digital image relative to the template 72 and other parameters specified by the user using the interface at step 52, as these will affect the generation of the 3D model 78, and hence the point cloud model 106. As a result of step 62, the SSLE depicting the object is produced.

[0078] In embodiments, steps 54 to 62 of the method 50 may be at least partially automated or fully automated so as to be performed with limited or no required intervention of a human user. For example, the laser control computer 6 may maintain or be in communication with a predefined computer directory. At the conclusion of step 54, the server computer 4 may send a file containing the generated 3D model 78 to the predefined computer directory. An application running on the server computer 4 may communicate, via an application programming interface (API), with an application running on the laser control computer 6 to notify the laser control computer 6 of the existence of a new file containing a 3D model 78 in the predefined computer directory. When so notified, a computer script running on the laser control computer 6 may automatically generate the point cloud model 106 and store a file containing the point cloud model 106 in the predefined computer directory. The laser control computer 6 may then control the laser device 8 to commence the engraving process, subject optionally to receiving an authorization from the user 14 of the laser control computer 10.

[0079] Referring to Figure 10 and 11 , the method 50 may be adapted for production of multiple SSLEs without the need for human supervision. For example, the server computer 4 may store a queue of SSLEs to be produced by a laser device 8. The server computer 4 may communicate this data to the laser control computer 6. Figure 10 shows a display screen of a laser control computer 6 showing a graphical user interface for tracking a queue of SSLEs to be produced based on such data. The interface may identify the shape and size of the transparent material block to be used for each SSLE. For example, Figure 10 shows a queue of three SSLEs to be produced, with a first SSLE having a trapezoidal prismatic shape, the second SSLE having rectangular prismatic shape and a third SSLE having a heart shape. Based on this information stored in memory, as shown in Figure 11 , the user 14 of the laser controlcomputer s loads transparent material blocks 18a, 18b, 18c having such shapes at assigned locations of the engraving table of the laser device 8. Additional transparent material blocks 18d, 18e, 18f are also loaded for additional SSLEs. Steps 54 through 62 as described above are performed sequentially in respect to each 2D digital image to be depicted by a 3D model 78 on each transparent material block 18a to 18f , so as to engrave the first through sixth SSLEs in sequential order. At step 62 described above, the control of the focal position of the laser, while the laser performs the subsurface engraving of the transparent material block to produce the SSLE, is further based at least on the respective location on the engraving table of the laser device that is stored and assigned to the transparent material block. The server computer 4 and / or the laser control computer 6 will keep track of which SSLEs have been produced so as to notify the user 14 of the laser control computer 6 when all of the transparent material blocks 18a to 18f have been engraved, and the engraving table of the laser device 8 is ready for a new batch of orders. In this manner, the laser device 8 may be pre-loaded with a plurality of transparent material blocks 18a to 18f , and left without human supervision (e.g., during evenings and weekends) to produce multiple SSLEs.

[0080] While the description contained herein constitutes a plurality of embodiments of the present disclosure, it will be appreciated that the present disclosure is susceptible to further modification and change without departing from the fair meaning of the accompanying claims.

[0081] Although preferred embodiments of the invention have been described herein in detail, it will be understood by those skilled in the art that variations may be made thereto without departing from the spirit of the invention or the scope of the appended claims.PARTS LIST2 system4 server computer4a server workstation4b, 4c worker computers6 laser control computer8 laser device10 consumer computerkiosk user of server computer user of laser control computer user of consumer computer transparent material block processor of server computer memory of server computer , 39 instructions for producing SSLE processor of laser control computer memory of laser control computer laser diode of laser device actuator for adjusting laser focal position actuator for adjusting laser focal depth processor of consumer computer memory of consumer computer touch screen of consumer computer digital camera of consumer computer -62 method for producing SSLE and steps thereof 2D digital image2D template of transparent material block for SSLE virtual button labelled "Submit Order" 3D model3D template of transparent material block for SSLE-98 method for training machine learning model and steps thereof2 virtual button labelled "Pass" 4 virtual button labelled "Fail" 6 point cloud model

Claims

CLAIMS1 . A method for producing a subsurface laser engraving (SSLE) depicting an object, the method comprising: using at least one processor, generating a three-dimensional (3D) model for the object based on a two-dimensional (2D) digital image file of the object, wherein the generating comprises applying a machine learning (ML) model to the 2D digital image file, and wherein the ML model is trained using a training dataset comprising training input 2D digital image files and respective training output 3D models, wherein each training input 2D digital image file and the respective training output 3D model depicts a respective training object; using the at least one processor, generating a point cloud model for the object based at least on the 3D model for the object; and using the at least one processor, controlling a focal position and a focal depth of a laser, based at least on the point cloud model for the object, while the laser performs subsurface engraving of a transparent material block to produce the SSLE comprising a depiction of the object.

2. The method of claim 1 , wherein the method comprises, using the at least one processor, causing a display device to display at least one interface configured to permit a user to select the 2D digital image file to be used for the generating of the 3D model of the object by selecting the 2D digital image file from a plurality of stored 2D digital images or by activating a digital camera to generate the 2D digital image file; and wherein the generating of the 3D model is based on the 2D digital image file that is selected by the user using the at least interface.

3. The method of claim 1 , wherein the method comprises, using the at least one processor, causing a display device to display at least one interface configured to permit a user to specify a position of the 2D digital image file relative to a template of the transparent material block to be engraved to produce the SSLE; andwherein the controlling of the focal position of the laser, while the laser performs the subsurface engraving of the transparent material block to produce the SSLE comprising the depiction of the object, is further based on the position of the 2D digital image file relative to the template that is specified by the user using the at least one interface.

4. The method of any one of claims 1 to 3, wherein the method comprises, using the at least one processor, receiving an indication that the 3D model for the object that was generated is satisfactory; and wherein the step of generating the point cloud model for the object based at least on the 3D model for the object is conditional on receiving the indication that the 3D model is satisfactory.

5. The method of any one of claims 1 to 4, wherein the at least one processor comprises a processor of at least one server computer located remotely from the laser device, wherein the processor of the at least one server computer performs at least the step of generating the 3D model for the object based on the 2D digital image file of the object.

6. The method of any one of claims 1 to 5, wherein the SSLE to be produced is one of a plurality of SSLEs to be produced by engraving a plurality of transparent material blocks, wherein a respective location on an engraving table of the laser device is assigned to each of the plurality of the transparent material blocks and stored in a memory; and wherein the step of controlling of the focal position of the laser, while the laser performs the subsurface engraving of the transparent material block to produce the SSLE comprising the depiction of the object, is further based at least on the respective location on the engraving table of the laser device that is stored and assigned to the transparent material block.

7. A system for producing a subsurface laser engraving (SSLE) depicting an object, for use with a laser device comprising a laser diode for generating a laser having a focal position and focal depth that are controllable, the system comprising: at least one processor operatively connected to the laser device and operatively connected to at least one memory comprising at least one non- transitory computer readable medium storing instructions executable by at least one processor to implement a method comprising: generating a three-dimensional (3D) model for the object based on a two- dimensional (2D) digital image file of the object, wherein the generating comprises applying a machine learning (ML) model to the 2D digital image file, and wherein the ML model is trained using a training dataset comprising training input 2D digital image files and respective training output 3D models, wherein each training input 2D digital image file and the respective training output 3D model depicts a respective training object; generating a point cloud model for the object based at least on the 3D model for the object; and controlling the focal position and the focal depth of the laser, based at least on the point cloud model for the object, while the laser performs subsurface engraving of a transparent material block to produce the SSLE depicting the object.

8. The system of claim 7, wherein the method comprises causing a display device to display at least one interface configured to permit a user to select the 2D digital image file to be used for the generating of the 3D model of the object by selecting the 2D digital image file from a plurality of stored 2D digital images or by activating a digital camera to generate the 2D digital image file; and wherein the generating of the 3D model is based on the 2D digital image file that is selected by the user using the at least interface.

9. The system of claim 7, wherein the method comprises causing a display device to display at least one interface configured to permit a user to specify a position of the 2D digital image file relative to a template of the transparent material block to be engraved to produce the SSLE; and wherein the controlling of the focal position of the laser, while the laser performs the subsurface engraving of the transparent material block to produce the SSLE comprising the depiction of the object, is further based on the position of the 2D digital image file relative to the template that is specified by the user using the at least one interface.

10. The system of any one of claims 7 to 9, wherein the method comprises receiving an indication that the 3D model for the object that was generated is satisfactory; and wherein the step of generating the point cloud model for the object based at least on the 3D model for the object is conditional on receiving the indication that the 3D model is satisfactory.11 . The system of any one of claims 7 to 10, wherein the at least one processor comprises a processor of at least one server computer located remotely from the laser device, wherein the processor of the at least one server computer performs at least the step of generating the 3D model for the object based on the 2D digital image file of the object.

12. The system of any one of claims 7 to 11 , wherein the SSLE to be produced is one of a plurality of SSLEs to be produced by engraving a plurality of transparent material blocks, wherein a respective location on an engraving table of the laser device is assigned to each of the plurality of the transparent material blocks and stored in a memory; and wherein the step of controlling of the focal position of the laser, while the laser performs the subsurface engraving of the transparent material block to produce the SSLE comprising the depiction of the object, is further basedat least on the respective location on the engraving table of the laser device that is stored and assigned to the transparent material block.

13. The system of claim 8 or 9, wherein the system comprises a kiosk comprising the display device and the laser device.

14. A computer program product for producing a subsurface laser engraving (SSLE) depicting an object, the computer program product comprising at least one non-transitory computer readable medium storing instructions executable by at least one processor operatively connected to a laser device comprising a laser diode for generating a laser having a focal position and a focal depth that are controllable by the at least one processor, to implement a method comprising: generating a three-dimensional (3D) model for the object based on a two- dimensional (2D) digital image file of the object, wherein the generating comprises applying a machine learning (ML) model to the 2D digital image file, and wherein the ML model is trained using a training dataset comprising training input 2D digital image files and respective training output 3D models, wherein each training input 2D digital image file and the respective training output 3D model depicts a respective training object; generating a point cloud model for the object based at least on the 3D model for the object; and controlling the focal position and the focal depth of the laser, based at least on the point cloud model for the object, while the laser performs subsurface engraving of a transparent material block to produce the SSLE depicting the object.

15. The computer program product of claim 14, wherein the method comprises causing a display device to display at least one interface configured to permit a user to select the 2D digital image file to be used for the generating of the 3D model of the object by selecting the 2D digital image file from a plurality of stored 2D digital images or by activating a digital camera to generate the 2D digital image file; andwherein the generating of the 3D model is based on the 2D digital image file that is selected by the user using the at least interface.

16. The computer program product of claim 14, wherein the method comprises causing a display device to display at least one interface configured to permit a user to specify a position of the 2D digital image file relative to a template of the transparent material block to be engraved to produce the SSLE; and wherein the controlling of the focal position of the laser, while the laser performs the subsurface engraving of the transparent material block to produce the SSLE comprising the depiction of the object, is further based on the position of the 2D digital image file relative to the template that is specified by the user using the at least one interface.

17. The computer program product of any one of claims 14 to 16, wherein the method comprises receiving an indication that the 3D model for the object that was generated is satisfactory; and wherein the step of generating the point cloud model for the object based at least on the 3D model for the object is conditional on receiving the indication that the 3D model is satisfactory.

18. The computer program product of any one of claims 14 to 17, wherein the SSLE to be produced is one of a plurality of SSLEs to be produced by engraving a plurality of transparent material blocks, wherein a respective location on an engraving table of the laser device is assigned to each of the plurality of the transparent material blocks and stored in a memory; and wherein the step of controlling of the focal position of the laser, while the laser performs the subsurface engraving of the transparent material block to produce the SSLE comprising the depiction of the object, is further based at least on the respective location on the engraving table of the laser device that is stored and assigned to the transparent material block.

Images