Method, system, device and storage medium for manufacturing cylindrical grating

Abstract

Embodiments of the present specification provide a method, system, device, and storage medium for manufacturing a lenticular grating. The method includes performing a depth analysis on a 2D target image to determine depth information of the 2D target image; determining light distribution information based on the depth information; determining reference values ​​for structural parameters of each layer of the lenticular grating based on the light distribution information; and manufacturing the lenticular grating based on the reference values ​​for the structural parameters of each layer of the lenticular grating, wherein the lenticular grating is configured to print a 3D grating painting corresponding to the 2D target image.

Description

Technical Field

[0001] The present invention relates to the field of lenticular grating production, and in particular to a method, system, device and storage medium for producing lenticular grating using a hierarchical molding process. Background Art

[0002] In 3D lenticular image display technology, lenticular lenses are a key component in achieving stereoscopic display. Through a specialized optical structure, they project different images to the user's left and right eyes, creating a 3D visual effect. However, the molding process used to produce lenticular lenses is inefficient for processing the complex grating structure, making it difficult to ensure grating uniformity and accuracy. This results in unstable image quality in 3D lenticular images, and can easily lead to issues such as image blur, color distortion, and visual disturbances.

[0003] Therefore, it is necessary to provide a method, system, device and storage medium for manufacturing a lenticular grating, which can prepare a lenticular grating with a complex structure, while improving the preparation efficiency of the lenticular grating and ensuring the accuracy and imaging quality of the lenticular grating. Summary of the Invention

[0004] One or more embodiments of the present specification provide a method for manufacturing a lenticular lens grating, the method comprising: performing depth analysis on a 2D target image to determine depth information of the 2D target image; determining light distribution information based on the depth information; determining reference values ​​for structural parameters of each of the multiple layers of the lenticular lens grating based on the light distribution information; and manufacturing the lenticular lens grating based on the reference values ​​for the structural parameters of each layer of the lenticular lens grating, wherein the lenticular lens grating is configured to print a 3D grating painting corresponding to the 2D target image.

[0005] In some embodiments, the depth analysis of the 2D target image to determine the depth information of the 2D target image includes: obtaining an algorithm selection model, where the algorithm selection model is a trained machine learning model; using the algorithm selection model to process the 2D target image to select a target depth information estimation algorithm from multiple alternative depth information estimation algorithms; and using the target depth information estimation algorithm to process the 2D target image to determine the depth information of the 2D target image.

[0006] In some embodiments, determining the light distribution information based on the depth information includes: determining Gaussian distribution information of the depth information; and determining the light distribution information based on the Gaussian distribution information.

[0007] In some embodiments, determining the light distribution information based on the Gaussian distribution information includes: determining multiple groups of alternative light distribution information; determining predicted Gaussian distribution information for each group of alternative light distribution information; and selecting one group from the multiple groups of alternative light distribution information as the light distribution information based on the Gaussian distribution information and the predicted Gaussian distribution information corresponding to each group of alternative light distribution information.

[0008] In some embodiments, the manufacturing of the lenticular grating based on the reference values ​​of the structural parameters of each layer of the lenticular grating includes: determining reference molding parameters for each layer of the lenticular grating based on the reference values ​​of the structural parameters of the layer; controlling a molding roller device to process the raw materials corresponding to the layer based on the reference molding parameters to manufacture the layer; and assembling the manufactured multiple layers to generate the lenticular grating.

[0009] In some embodiments, before controlling the molding roller device to process the raw material corresponding to the layer based on the reference molding parameters to produce the layer, the method further includes: using at least one sensor to calibrate the molding roller device to determine that the difference between the molding parameters of the molding roller device and the reference molding parameters is less than a preset threshold.

[0010] In some embodiments, based on the reference molding parameters, the molding roller equipment is controlled to process the raw materials corresponding to the layer to produce the layer, including: during the production process, using at least one sensor to detect the molding parameters of the molding roller equipment; based on the detection results and the reference molding parameters, the molding roller equipment is adjusted in real time.

[0011] One or more embodiments of the present specification provide a system for producing a lenticular grating, the system comprising: an analysis module configured to perform depth analysis on a 2D target image to determine depth information of the 2D target image; a first determination module configured to determine light distribution information based on the depth information; a second determination module configured to determine reference values ​​of structural parameters of each of the multiple layers of the lenticular grating based on the light distribution information; and a production module configured to produce the lenticular grating based on the reference values ​​of the structural parameters of each layer of the lenticular grating, wherein the lenticular grating is configured to print a 3D grating painting corresponding to the 2D target image.

[0012] One or more embodiments of the present specification provide a device for manufacturing a lenticular grating, the device comprising at least one processor and at least one memory; the at least one memory is used to store computer instructions; the at least one processor is used to execute at least part of the computer instructions to implement a method for manufacturing a lenticular grating according to any one of the above embodiments.

[0013] One or more embodiments of this specification provide a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes a method for manufacturing a lenticular grating as described in any one of the above embodiments.

[0014] According to the above scheme, a cylindrical grating with a complex structure can be prepared, and the accuracy and imaging quality of the cylindrical grating are guaranteed while improving the preparation efficiency of the cylindrical grating. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] This specification will be further described in the form of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting, and in these embodiments, like numbers represent like structures, wherein:

[0016] Figure 1 is a schematic diagram of an application scenario of a lenticular grating manufacturing system according to some embodiments of this specification;

[0017] Figure 2 is an exemplary module diagram of a system for manufacturing a lenticular grating according to some embodiments of this specification;

[0018] Figure 3 is an exemplary flow chart of a method for manufacturing a lenticular grating according to some embodiments of this specification;

[0019] Figure 4 is an exemplary flow chart of a process for determining depth information of a 2D target image according to some embodiments of this specification;

[0020] Figure 5 is an exemplary schematic diagram of a process for manufacturing a lenticular grating according to some embodiments of this specification;

[0021] Figure 6 is an exemplary schematic diagram of a molding roller apparatus according to some embodiments of the present specification. DETAILED DESCRIPTION

[0022] To more clearly illustrate the technical solutions of the embodiments of this specification, the following briefly describes the drawings required for describing the embodiments. Obviously, the drawings described below are merely examples or embodiments of this specification. Those skilled in the art can apply this specification to other similar scenarios based on these drawings without inventive effort. Unless otherwise apparent from the context or otherwise noted, the same reference numerals in the figures represent the same structure or operation.

[0023] It should be understood that the terms "system," "device," "unit," and / or "module" used herein are a method for distinguishing different components, elements, parts, portions, or assemblies at different levels. However, if other terms can achieve the same purpose, the terms may be replaced by other expressions.

[0024] As used in this specification and claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" do not refer to the singular but also include the plural. Generally speaking, the terms "comprises" and "include" only indicate the inclusion of the steps and elements specifically identified, and these steps and elements do not constitute an exclusive list. A method or apparatus may also include other steps or elements.

[0025] Flowcharts are used throughout this specification to illustrate the operations performed by systems according to embodiments of this specification. It should be understood that preceding or following operations do not necessarily need to be performed in exact order. Instead, the steps may be processed in reverse order or simultaneously. Furthermore, other operations may be added to these processes, or one or more operations may be removed from these processes.

[0026] Figure 1 Schematic diagram of an application scenario of a cylindrical grating manufacturing system according to some embodiments of this specification. Figure 1 As shown, the application scenario 100 may include a molding roller device 110 , a processor 120 , a network 130 , a storage device 140 , a terminal 150 , and a sensor 160 .

[0027] The molding roller apparatus 110 is configured to process a raw material (e.g., polystyrene) to produce a lenticular lens. Figure 6 As shown, the embossing roller apparatus 110 may include a balancing shaft 610, an embossing roller 620, and a machine tool structure 630. The balancing shaft 610 is configured to reduce vibration during the rotation of the embossing roller 620, thereby ensuring smoother and more stable operation of the embossing roller 620. The embossing roller 620 is configured to press the raw material introduced therein to produce a lenticular lens. The machine tool structure 630 is configured to support and position the balancing shaft 610 and the embossing roller 620.

[0028] The processor 120 is configured to process data and / or information obtained from the molding roller device 110, the storage device 140, the terminal 150 and / or the sensor 160. For example, the processor 120 may perform a depth analysis on the 2D target image to determine the depth information of the 2D target image. For another example, the processor 120 may determine the light distribution information based on the depth information. For another example, the processor 120 may determine the reference value of the structural parameter of each layer of the lenticular grating based on the light distribution information. For another example, the processor 120 may produce the lenticular grating based on the reference value of the structural parameter of each layer of the lenticular grating. In some embodiments, the processor 120 may send the processing result to the terminal 150. For example, the processor 120 may send the reference value of the structural parameter of each layer of the lenticular grating to the terminal 150 and display it on one or more display devices of the terminal 150.

[0029] In some embodiments, the processor 120 can be a single server or a server group. The server group can be centralized or distributed. In some embodiments, the processor 120 can be local or remote. In some embodiments, the processor 120 can be connected to the molding roller device 110, storage device 140, terminal 150, and / or sensor 160 via the network 130 or directly to access information and / or data stored thereon. In some embodiments, the processor 120 can be implemented on a cloud platform. By way of example only, the cloud platform can include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-cloud, or any combination thereof.

[0030] The network 130 may include any suitable network that can facilitate data exchange and communication connections. For example, the processor 120 may obtain detection results of the molding roller device 110 from the sensor 160 via the network 130. In some embodiments, the network 130 may be any one or more of a wired network or a wireless network.

[0031] The storage device 140 can store data, instructions, and / or any other information. In some embodiments, the storage device 140 can store data obtained from the molding roller device 110, the processor 120, the terminal 150, and / or the sensor 160. In some embodiments, the storage device 140 can store data and / or instructions used by the processor 120 to execute or use the exemplary methods described herein. In some embodiments, the storage device 140 can include a mass storage device, a removable memory, a volatile read-write memory, a read-only memory (ROM), or the like, or any combination thereof. In some embodiments, the storage device 140 can be implemented on a cloud platform. In some embodiments, the storage device 140 can be part of the processor 120.

[0032] Terminal 150 can implement user interaction. In some embodiments, terminal 150 can include one or any combination of a mobile device 150-1, a tablet computer 150-2, a laptop computer 150-3, or other devices with input and / or output functions. In some embodiments, terminal 150 can receive data (e.g., reference values ​​for structural parameters of each layer of the lenticular lens) from processor 120 and present this data. In some embodiments, terminal 150 can be omitted.

[0033] The sensor 160 is configured to detect the molding roller device 110. For example, the sensor 160 can detect the molding parameters of the molding roller device 110 to obtain a detection result. The sensor 160 can include various types of sensors, such as a temperature sensor, a pressure sensor, and the like.

[0034] It should be noted that application scenario 100 is provided for illustrative purposes only and is not intended to limit the scope of this specification. A person skilled in the art can make various modifications or variations based on the description of this specification. For example, application scenario 100 can be implemented on other devices to achieve similar or different functions. However, such changes and modifications do not deviate from the scope of this specification.

[0035] Figure 2 is an exemplary module diagram of a lenticular grating production system 200 (hereinafter referred to as system 200) according to some embodiments of this specification. In some embodiments, the system 200 may include an analysis module 210, a first determination module 220, a second determination module 230, and a production module 240. In some embodiments, the system 200 may be composed of Figure 1 The processor 120 shown implements .

[0036] The analysis module 210 is configured to perform depth analysis on the 2D target image to determine the depth information of the 2D target image. For more description on determining the depth information, please refer to steps 310 and Figure 4 and its related descriptions.

[0037] The first determining module 220 is configured to determine light distribution information based on the depth information. For more information about determining the light distribution information, please refer to step 320 and its related description.

[0038] The second determining module 230 is configured to determine a reference value of a structural parameter of each layer in the lenticular lens grating based on the light distribution information. For more information on determining the reference value of the structural parameter of each layer, please refer to step 330 and its related description.

[0039] The manufacturing module 240 is configured to manufacture the lenticular grating based on the reference values ​​of the structural parameters of each layer of the lenticular grating. For more information on manufacturing the lenticular grating, please refer to steps 340 and Figure 5 and its related descriptions.

[0040] In some embodiments, the system 200 may further include a verification detection module 250 .

[0041] The verification detection module 250 is configured to verify the embossing roller device using at least one sensor before manufacturing the lenticular grating layer to determine whether the difference between the embossing parameters of the embossing roller device and the reference embossing parameters is less than a preset threshold.

[0042] In some embodiments, the verification and detection module 250 is further configured to detect the molding parameters of the molding roller device using at least one sensor during the process of manufacturing the lenticular lens grating; and to make real-time adjustments to the molding roller device based on the detection results and the reference molding parameters. For more information about the verification and detection module, please refer to Figure 5 and its related descriptions.

[0043] It should be noted that the above description of the system 200 and its modules is for convenience only and does not limit this specification to the scope of the embodiments. It is understood that those skilled in the art, after understanding the principles of the system, may arbitrarily combine the modules or form subsystems connected to other modules without departing from the principles. In some embodiments, Figure 2 The analysis module 210, first determination module 220, second determination module 230, production module 240, and verification and detection module 250 disclosed herein may be different modules within a single system, or a single module may implement the functions of two or more of the aforementioned modules. For example, the modules may share a storage module, or each module may have its own storage module. Such variations are within the scope of protection of this specification.

[0044] Figure 3 is an exemplary flow chart of a method for manufacturing a cylindrical grating according to some embodiments of this specification. In some embodiments, process 300 can be executed by processor 120 or system 200. For example, process 300 can be stored in the form of a program or instructions in storage device 140, and when processor 120 or system 200 executes the instructions, process 300 can be implemented. The operational diagram of process 300 presented below is illustrative. In some embodiments, the process can be completed using one or more additional operations not described and / or one or more operations not discussed. In addition, Figure 3 The order in which the operations of flow 300 are illustrated and described below is not intended to be limiting.

[0045] Step 310 : Perform depth analysis on the 2D target image to determine depth information of the 2D target image.

[0046] A 2D target image refers to a 2D image to be processed. For example, a 2D target image needs to be converted into a 3D raster image. In some embodiments, the 2D target image can be a real image captured by an image acquisition device such as a camera, or a virtual image generated by a computer.

[0047] Depth information refers to the distance between each point in a 2D target image and a reference point. A reference point is a point selected as a reference. For example, if the 2D target image is a real image, the reference point may be the location of the lens of the image acquisition device. For another example, if the 2D target image is a virtual image, the reference point may be the location of the virtual lens corresponding to the virtual image.

[0048] In some embodiments, the processor may process the 2D target image using a depth information estimation algorithm to determine the depth information of the 2D target image. The depth information estimation algorithm may include a LeRes algorithm, a Midas algorithm, a Structure From Motion (SFM) algorithm, a ResNet algorithm, a MiDas algorithm, a ZoeDepth algorithm, and the like. In some embodiments, the processor may also process the 2D target image using a depth information determination model to determine the depth information of the 2D target image. The depth information determination model may be a machine learning model, such as a deep neural network (DNN) model.

[0049] In some embodiments, the processor may process the 2D target image using an algorithm selection model, select a target depth information estimation algorithm, and process the 2D target image using the target depth information estimation algorithm to determine the depth information of the 2D target image. For more information about the aforementioned embodiments, see Figure 4 and its related descriptions.

[0050] Step 320: Determine light distribution information based on the depth information.

[0051] Light distribution information refers to information that reflects how light propagates in space. For example, light distribution information may include the direction, brightness, and distribution pattern of light in space. In some embodiments, light distribution information can be represented by parameters. For example, the direction of light propagation in space can be represented by the propagation angle or diffraction angle of the light. In another example, the brightness of the light can be represented by the light intensity. In another example, the distribution pattern of the light can be represented by the density of the light in space.

[0052] In some embodiments, the light distribution information is related to an ideal light distribution that the lenticular lens can achieve. When the lenticular lens can achieve the ideal light distribution, the 3D lenticular painting produced based on the lenticular lens has a better display effect.

[0053] In some embodiments, the storage device may pre-store correspondences between different light distribution information and depth information, and the processor may access the storage device based on the determined depth information to generate light distribution information through the correspondences.

[0054] In some embodiments, the processor may determine Gaussian distribution information of the depth information; and determine the light distribution information based on the Gaussian distribution information.

[0055] Gaussian distribution information refers to a Gaussian distribution used to describe depth information.

[0056] In some embodiments, the processor can use the formula based on the depth information Gaussian distribution information is calculated. Where P(z) is the Gaussian distribution information; z is the depth value, ranging from 0 to 255; σ is the standard deviation of the depth; and μ is the average depth.

[0057] In some embodiments, the processor may first determine the diffraction angle θ of the lenticular grating based on the depth value z in the Gaussian distribution information; determine the propagation angle of the light based on the principles of geometric optics (e.g., the law of refraction) and the diffraction angle; calculate the light intensity based on the diffraction angle and Lambert's law; and determine the spatial distribution density of the light based on a density distribution function. For example, the density distribution function may be expressed as D(x, y, z), where x and y represent the position of the light in space, and z is the depth value in the Gaussian distribution information.

[0058] In some embodiments, the processor can determine multiple sets of alternative light distribution information; determine predicted Gaussian distribution information for each set of alternative light distribution information; and select one set from the multiple sets of alternative light distribution information as the light distribution information based on the Gaussian distribution information and the predicted Gaussian distribution information corresponding to each set of alternative light distribution information.

[0059] Alternative light distribution information refers to available light distribution information. For example, the alternative light distribution information may include parameters such as alternative light propagation angles, alternative light intensities, and alternative light distribution densities. The alternative light distribution information can be determined through data simulation, user specification, or a brute force search algorithm.

[0060] The predicted Gaussian distribution information refers to the predicted Gaussian distribution information corresponding to the set of candidate light distribution information.

[0061] In some embodiments, the processor may process the alternative light distribution information through a Gaussian distribution prediction model to determine the predicted Gaussian distribution information corresponding to the group of alternative light distribution information. The Gaussian distribution prediction model is a machine learning model, such as a deep neural network (DNN) model. The Gaussian distribution prediction model may be generated based on training samples, and the training samples include sample light distribution information and its corresponding gold standard Gaussian distribution information. For example, the training samples may be determined based on historical analysis records, and the historical analysis records include historical depth information, historical Gaussian distribution information determined based on the historical depth information, and historical light distribution information determined based on the historical Gaussian distribution information. The historical Gaussian distribution information may be used as gold standard Gaussian distribution information, and the historical light distribution information may be used as sample light distribution information.

[0062] In some embodiments, the processor may further determine predicted Gaussian distribution information corresponding to the set of alternative light distribution information based on the alternative light distribution information through optical propagation, diffraction theory, and refraction parameters of the propagation medium.

[0063] In some embodiments, the processor may select a set of candidate light distribution information that is closest to the predicted Gaussian distribution information and the Gaussian distribution information, and determine it as the light distribution information.

[0064] In some embodiments of the present specification, one set of alternative light distribution information is selected as the light distribution information, so that the Gaussian distribution information corresponding to the determined light distribution information and the Gaussian distribution information corresponding to the depth information are as close as possible, thereby making the 3D grating painting printed based on the produced lenticular grating consistent with the depth information determined in step 310, thereby improving the accuracy of lenticular grating production.

[0065] Step 330 : Determine a reference value of a structural parameter of each layer in the multi-layer lenticular grating based on the light distribution information.

[0066] A lenticular lens is a grating composed of a series of tiny cylindrical convex lenses. A lenticular lens can include multiple layers to achieve periodic refraction of light. A lenticular lens is configured to print a 3D grating image corresponding to a 2D target image.

[0067] 3D lenticular art refers to a flat image that creates a three-dimensional effect. 3D lenticular art can then be printed into a physical painting, which can display different content at different angles, and even create a dynamic, visually captivating effect.

[0068] The reference value of the structural parameter refers to the ideal value of the structural parameter. The structural parameter refers to the parameters related to the structure of each layer of the lenticular lens. For example, the structural parameters may include the shape, size, and spacing of each layer of the lenticular lens.

[0069] In some embodiments, the processor can calculate the pitch of the lenticular grating using the grating equation d sinθ = mλ. Where d is the pitch of the lenticular grating; θ is the diffraction angle of the lenticular grating; m is the diffraction order of the lenticular grating; and λ is the wavelength of light. In some embodiments, the processor can calculate the size of the lenticular grating based on the light distribution information using the formula a sinθ = mλ. Where a is the size of the lenticular grating.

[0070] Step 340 : Manufacturing the lenticular grating based on the reference values ​​of the structural parameters of each layer of the lenticular grating.

[0071] In some embodiments, the processor may control the molding roller device to produce each layer of the lenticular grating through a hierarchical molding process based on reference values ​​of the structural parameters of each layer, and assemble the produced multiple layers to generate the lenticular grating.

[0072] The hierarchical molding process refers to the process of using a molding roller device to produce each layer of the lenticular lens grating in layers. When producing each layer, the molding roller device can be controlled based on the reference value of the structural parameters of the layer, so that the structural parameters of the layer produced by the molding roller device are as close to the reference value as possible. For more information on the production of lenticular lens gratings, please refer to Figure 5 and its related descriptions.

[0073] In some embodiments of this specification, a laminated molding process is used to fabricate lenticular gratings in layers. Compared to the integrated molding process used to fabricate lenticular gratings, the laminated molding process can produce lenticular gratings with complex structures, improving the accuracy of lenticular grating fabrication and enabling lenticular gratings to achieve superior 3D grating image display effects. Furthermore, in some embodiments of this specification, by processing the light distribution information corresponding to a 2D target image and utilizing high-precision light field control technology, reference values ​​for the structural parameters of each layer of the lenticular grating are determined to guide the fabrication of the lenticular grating, thereby ensuring the accuracy and imaging quality of the lenticular grating.

[0074] It should be noted that the above description of process 300 is for illustration and purpose only and does not limit the scope of application of this specification. Those skilled in the art may make various modifications and alterations to process 300 under the guidance of this specification. However, such modifications and alterations are still within the scope of this specification.

[0075] Figure 4 is an exemplary flow chart of a process for determining depth information of a 2D target image according to some embodiments of this specification.

[0076] In some embodiments, the processor may obtain an algorithm selection model 420; process the 2D target image 410 using the algorithm selection model 420 to select a target depth information estimation algorithm 430 from a plurality of alternative depth information estimation algorithms; and process the 2D target image 410 using the target depth information estimation algorithm 430 to determine depth information 440 of the 2D target image.

[0077] The candidate depth information estimation algorithm refers to a depth information estimation algorithm that can be selected. For example, the candidate depth information estimation algorithm may include the LeRes algorithm, the Midas algorithm, the SFM algorithm, the ResNet algorithm, the MiDas algorithm, the ZoeDepth algorithm, etc. The target depth information estimation algorithm 430 is a depth information estimation algorithm selected from the candidate depth information estimation algorithms and is suitable for processing the 2D target image.

[0078] The algorithm selection model 420 is a machine learning model used to select an appropriate depth information estimation algorithm for an input image based on the characteristics of the input image. For example, the algorithm selection model may include a deep neural network (DNN) model.

[0079] In some embodiments, the algorithm selection model 420 is an Adaptive Depth Perception Network (ADPN).

[0080] In some embodiments, the algorithm selection model 420 can be trained using multiple training samples with training labels. For example, multiple training samples can be input into the initial algorithm selection model, and the value of a loss function can be determined using the training labels and the output of the initial algorithm selection model. The parameters of the initial algorithm selection model are then iteratively updated based on the loss function. When pre-set iteration conditions are met, model training is complete, resulting in a trained algorithm selection model. Pre-set iteration conditions can include, for example, convergence of the loss function or a threshold number of iterations.

[0081] In some embodiments, the training samples include sample 2D target images of the sample object, and the training labels include a depth information estimation algorithm for the sample object. The training samples can be determined based on historical data. The training labels can be determined through manual annotation or automatically determined through data analysis. In some embodiments, the training samples and training labels can be determined by: obtaining image generation records; for each image generation record, determining whether the historical 3D raster images in the image generation record meet a preset condition; and in response to determining that the historical 3D raster images meet the preset condition, using the historical 2D images in the image generation record as training samples and using the historical depth information estimation algorithm in the image generation record as training labels.

[0082] An image generation record refers to a historical record of converting a 2D image into a 3D raster image. Each image generation record includes a historical 2D image, a historical depth information estimation algorithm, and a historical 3D raster image. The historical 3D raster image is generated based on the historical 2D image and the historical depth information estimation algorithm. In some embodiments, the processor can access the image generation record by accessing a storage device, record the 2D image in each image generation record as a historical 2D image, the corresponding 3D raster image as a historical 3D raster image, and the depth information estimation algorithm used in the conversion process as a historical depth information estimation algorithm.

[0083] In some embodiments, the processor may determine whether the historical 3D raster image meets a preset condition based on the off-screen distance of the historical 3D raster image and a preset off-screen distance. The off-screen distance may measure the visual effect of a target object in the 3D raster image (e.g., an off-screen effect or an on-screen effect). For example, the off-screen distance may be such that the target object in the 3D raster image has an off-screen effect of 3 centimeters. For example, the processor may calculate the difference between the off-screen distance of the historical 3D raster image and the preset off-screen distance. If the calculated difference is less than an off-screen difference threshold, the historical 3D raster image meets the preset condition. The off-screen difference threshold may be a default value, a preset value, etc.

[0084] In some embodiments of this specification, historical 2D images and historical depth information estimation algorithms corresponding to historical 3D raster images that meet preset conditions in image generation records are used as training samples and training labels. This enables automated determination of training samples and training labels, reducing manual labeling time and improving training efficiency. Furthermore, evaluating the suitability of the historical depth information estimation algorithm based on the resulting historical 3D raster images can improve the accuracy of the determined training labels.

[0085] In some embodiments of the present specification, using an algorithm selection model instead of manually selecting a target depth information estimation algorithm can improve the accuracy of the selected target depth information estimation algorithm, while improving efficiency and reducing human intervention.

[0086] Figure 5 is an exemplary schematic diagram of a process for generating a cylindrical grating according to some embodiments of the present specification.

[0087] In some embodiments, for each layer of the lenticular grating, the processor can determine a reference molding parameter 520 based on a reference value 510 of the structural parameter of the layer; based on the reference molding parameter 520, control the molding roller device 110 to process the raw material corresponding to the layer to produce the layer 530 of the lenticular grating; and assemble the produced multiple layers to generate the lenticular grating 540.

[0088] Reference molding parameters 520 are molding parameters corresponding to the desired lenticular grating. Molding parameters refer to parameters related to the operating state of the molding roller device 110 during molding. For example, molding parameters may include temperature, pressure, and molding roller speed during molding.

[0089] It is understandable that the structural parameters of the lenticular grating obtained based on different molding parameters are also different. For example, due to the thermal expansion of the raw materials, different molding temperatures may result in different spacing of the lenticular grating. In addition, improper molding temperature control may also cause the optical properties of the raw materials (e.g., refractive index) to change, thereby affecting the focusing ability of the lenticular grating and the light transmission efficiency. For another example, the molding pressure has a significant impact on the microstructure of the lenticular grating. Uneven or excessive molding pressure will cause the surface of the lenticular grating to have tiny protrusions or depressions, thereby affecting the scattering and diffraction characteristics of light and reducing the contrast and clarity of the printed 3D grating image. For another example, the speed of the molding roller will affect the flow time and cooling rate of the raw materials in the mold, thereby affecting the geometric dimensions and optical properties of the lenticular grating. Excessive molding roller speed may cause unevenness between the layers of the lenticular grating. For another example, the rotation angle of the molding roller will affect the uniformity of the lenticular grating, thereby affecting the optical performance and imaging quality of the lenticular grating. Therefore, in order to ensure the optical performance and imaging quality of the lenticular grating, each molding roller needs to be precisely designed and adjusted to ensure the uniformity and accuracy of each layer of the prepared lenticular grating.

[0090] In some embodiments, the storage device may pre-store correspondences between different structural parameters and molding parameters, and the processor may access the storage device based on reference values ​​of the structural parameters of the layer and generate reference molding parameters through the correspondences.

[0091] In some embodiments of the present specification, by precisely controlling the temperature, pressure, and molding roller speed during the preparation of each layer of the lenticular grating, a lenticular grating structure with desired optical properties can be accurately manufactured, which not only improves production efficiency but also enhances the overall performance and imaging quality of the lenticular grating.

[0092] In some embodiments, before using the molding roller device 110 to process the raw material corresponding to the layer based on the reference molding parameters 520 to produce each layer, the processor can use at least one sensor 160 to calibrate the molding roller device 110 to determine that the difference between the molding parameters of the molding roller device 110 and the reference molding parameters 520 is less than a preset threshold.

[0093] The preset threshold value refers to the maximum value of the difference between the preset molding parameters and the reference molding parameters. For example, the preset temperature threshold value may be 0.5°C.

[0094] In some embodiments, the processor can calculate the difference between the molding parameters of the molding roller device and the reference molding parameters and determine whether the difference is less than a preset threshold. In response, the processor controls the molding roller device to process the raw material corresponding to the layer to produce the layer. If the difference is greater than the preset threshold, it indicates that the operating status of the molding roller device does not meet the requirements and needs to be adjusted to bring the molding parameters as close as possible to the reference molding parameters.

[0095] In some embodiments of the present specification, before manufacturing the lenticular lens grating, the molding roller equipment is calibrated to ensure the accuracy in the subsequent manufacturing process and avoid the waste of raw materials.

[0096] In some embodiments, during the manufacturing process, the processor may use at least one sensor 160 to detect the molding parameters of the molding roller device 110 ; and adjust the molding roller device 110 in real time based on the detection result and the reference molding parameters 520 .

[0097] The detection result refers to the real-time molding parameters of the molding roller equipment during the production process obtained by the sensor. For example, the detection result may include the real-time temperature, real-time pressure, real-time speed of the molding roller equipment during the production process.

[0098] In some embodiments, the processor can calculate the difference between the detection result and the reference molding parameter and determine whether the difference is greater than a difference threshold. In response, the processor can adjust the molding roller device in real time. For example, if the reference molding temperature is 150°C, the temperature difference threshold is 1°C, and the real-time temperature of the molding roller device during the production process obtained by the sensor is 152°C, in response to the difference between the real-time temperature and the reference molding temperature being 152°C - 150°C = 2°C > 1°C, the processor can control the molding roller device to lower the molding temperature.

[0099] In some embodiments of the present specification, the molding parameters are detected during the production process of the lenticular grating, and the molding parameters of the molding roller equipment are adjusted in real time, which can improve the accuracy and timeliness of the production process.

[0100] One or more embodiments of the present specification provide a device for manufacturing a lenticular grating, the device comprising at least one processor and at least one memory; the at least one memory is used to store computer instructions; the at least one processor is used to execute at least part of the computer instructions to implement a method for manufacturing a lenticular grating according to any one of the above embodiments.

[0101] One or more embodiments of this specification provide a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes a method for manufacturing a lenticular grating as described in any one of the above embodiments.

[0102] While the basic concepts have been described above, it will be apparent to those skilled in the art that the detailed disclosure is merely illustrative and does not limit this specification. Although not explicitly stated herein, various modifications, improvements, and revisions to this specification may be made by those skilled in the art. Such modifications, improvements, and revisions are suggested in this specification and remain within the spirit and scope of the exemplary embodiments of this specification.

[0103] This specification also uses specific terms to describe the embodiments of this specification. For example, "one embodiment," "an embodiment," and / or "some embodiments" refer to a feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that references to "one embodiment," "an embodiment," or "an alternative embodiment" two or more times in different locations in this specification do not necessarily refer to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of this specification may be appropriately combined.

[0104] In addition, unless expressly stated in the claims, the order of the processing elements and sequences, the use of alphanumeric characters, or the use of other names described in this specification are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some of the invention embodiments currently considered useful through various examples, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the spirit and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0105] Similarly, it should be noted that, in order to simplify the presentation of this specification and thus facilitate understanding of one or more embodiments of the invention, the foregoing descriptions of the embodiments of this specification sometimes combine multiple features into a single embodiment, figure, or description thereof. However, this disclosure method does not imply that the subject matter of this specification requires more features than those recited in the claims. In fact, an embodiment may have fewer features than all of the features of a single disclosed embodiment.

[0106] In some embodiments, numbers are used to describe the quantity of components and attributes. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise stated, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the description and claims are approximate values, which may change according to the required characteristics of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the settings of such numerical values ​​are as accurate as possible within the feasible range.

[0107] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, and documents, cited in this specification is hereby incorporated by reference in its entirety. This includes application history documents that are inconsistent with or conflict with the content of this specification, as well as documents (currently or subsequently attached to this specification) that limit the broadest scope of the claims of this specification. It should be noted that if the descriptions, definitions, and / or terminology used in the accompanying materials are inconsistent or conflicting with the content of this specification, the descriptions, definitions, and / or terminology used in this specification will control.

[0108] Finally, it should be understood that the embodiments described in this specification are intended only to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, by way of example and not limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly described and illustrated in this specification.

Claims

1. A method for manufacturing a cylindrical grating, characterized in that: The method comprises: Performing depth analysis on the 2D target image to determine depth information of the 2D target image; determining light distribution information based on the depth information; determining a reference value of a structural parameter of each layer in the multi-layer lenticular grating based on the light distribution information; The lenticular lens is manufactured based on reference values ​​of structural parameters of each layer of the lenticular lens, and the lenticular lens is configured to print a 3D lenticular painting corresponding to the 2D target image.

2. The method according to claim 1, characterized in that The performing depth analysis on the 2D target image to determine depth information of the 2D target image includes: Obtain an algorithm selection model, where the algorithm selection model is a trained machine learning model; Processing the 2D target image using the algorithm selection model to select a target depth information estimation algorithm from a plurality of candidate depth information estimation algorithms; The 2D object image is processed using the object depth information estimation algorithm to determine depth information of the 2D object image.

3. The method according to claim 1, characterized in that The determining of light distribution information based on the depth information includes: Determining Gaussian distribution information of the depth information; The light distribution information is determined based on the Gaussian distribution information.

4. The method according to claim 3, characterized in that The determining the light distribution information based on the Gaussian distribution information includes: determining multiple sets of candidate light distribution information; For each set of candidate light distribution information, determine predicted Gaussian distribution information; Based on the Gaussian distribution information and the predicted Gaussian distribution information corresponding to each set of candidate light distribution information, one set is selected from the multiple sets of candidate light distribution information as the light distribution information.

5. The method according to claim 1, wherein The manufacturing of the lenticular grating based on the reference value of the structural parameter of each layer of the lenticular grating comprises: For each layer of the lenticular grating, determining reference molding parameters based on reference values ​​of the structural parameters of the layer; Based on the reference molding parameters, controlling the molding roller device to process the raw material corresponding to the layer to produce the layer; The fabricated multiple layers are assembled to generate the lenticular grating.

6. The method according to claim 5, characterized in that Before controlling the molding roller device to process the raw material corresponding to the layer based on the reference molding parameters to produce the layer, the method further comprises: The molding roller device is calibrated using at least one sensor to determine whether a difference between a molding parameter of the molding roller device and a reference molding parameter is less than a preset threshold.

7. The method according to claim 5, characterized in that The step of controlling the molding roller device to process the raw material corresponding to the layer based on the reference molding parameters to produce the layer comprises: During the manufacturing process, at least one sensor is used to detect the molding parameters of the molding roller device; Based on the detection results and the reference molding parameters, the molding roller equipment is adjusted in real time.

8. A system for manufacturing a cylindrical grating, characterized in that: The system comprises: an analysis module, configured to perform depth analysis on the 2D target image to determine depth information of the 2D target image; A first determining module is configured to determine light distribution information based on the depth information; a second determining module configured to determine a reference value of a structural parameter of each of the multiple layers of the lenticular grating based on the light distribution information; The manufacturing module is configured to manufacture the lenticular grating based on the reference value of the structural parameter of each layer of the lenticular grating, and the lenticular grating is configured to print a 3D grating painting corresponding to the 2D target image.

9. A device for manufacturing a cylindrical grating, characterized in that: The apparatus comprises at least one processor and at least one memory; The at least one memory is for storing computer instructions; The at least one processor is configured to execute at least part of the computer instructions to implement the method for manufacturing a lenticular grating according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the method for manufacturing a lenticular grating according to any one of claims 1 to 7.

Images