Smoothing method of three-dimensional hand model and electronic equipment

Abstract

The invention provides a smoothing method of a three-dimensional hand model and electronic equipment, which are used for removing shake of the three-dimensional hand model in a display process and improving user experience. Comprising the steps that for any hand image in a hand video stream, multiple model driving parameters of the hand image are acquired, and the model driving parameters are used for driving a preset three-dimensional hand model; for any model driving parameter in the plurality of model driving parameters, based on a preset quantization step size and a minimum value corresponding to the model driving parameter, obtaining a quantization index of the model driving parameter, the quantization index being used for representing an extreme value when the model driving parameter is quantized; quantizing the model driving parameter according to the quantization index of the model driving parameter to obtain a quantization value of the model driving parameter; and driving the three-dimensional hand model by using the quantized value of the model driving parameter to obtain a smoothed three-dimensional hand model corresponding to the hand image.

Description

Background Art

[0002] VR (Virtual Reality) technology provides users with an immersive gaming experience. As a form of interaction, 3D (Three Dimensions) gestures have the advantages of being easy to use and natural. 3D gestures have become an important part of interaction in the VR field. With the introduction of the concept of the metaverse in recent years and the innovative combination of 3D gestures and eye movement technology for product interaction by industry leaders, the market has paid unprecedented attention to 3D gestures.

[0003] However, 3D gestures are realized by driving a three-dimensional hand model, and jitter problems are prone to occur during the display of the three-dimensional hand model, affecting the user experience and interaction. Summary of the invention

[0004] The present application provides a three-dimensional hand model smoothing method and electronic device, which are used to smooth the three-dimensional hand model, remove the jitter of the three-dimensional hand model during the display process, and improve the user experience and interaction success rate.

[0005] In a first aspect, an embodiment of the present application provides a method for smoothing a three-dimensional hand model, the method comprising:

[0006] For any hand image in the hand video stream, obtain a plurality of model driving parameters of the hand image, wherein the model driving parameters are used to drive a preset three-dimensional hand model, wherein the hand image includes a left hand image or a right hand image;

[0007] For any one of the plurality of model-driven parameters, based on a preset quantization step size and a minimum value corresponding to the model-driven parameter, a quantization index of the model-driven parameter is obtained, wherein the quantization index is used to represent an extreme value when the model-driven parameter is quantized; and,

[0008] quantizing the model driving parameter according to the quantization index of the model driving parameter to obtain a quantized value of the model driving parameter;

[0009] The three-dimensional hand model is driven by using the quantized value of the model driving parameter to obtain a smoothed three-dimensional hand model corresponding to the hand image.

[0010] A second aspect of the present application provides an electronic device, including a processor and a memory, wherein the processor and the memory are connected via a bus;

[0011] The memory stores a computer program, and the processor is configured to perform the following operations based on the computer program:

[0012] For any hand image in the hand video stream, obtain a plurality of model driving parameters of the hand image, wherein the model driving parameters are used to drive a preset three-dimensional hand model, wherein the hand image includes a left hand image or a right hand image;

[0013] For any one of the plurality of model-driven parameters, based on a preset quantization step size and a minimum value corresponding to the model-driven parameter, a quantization index of the model-driven parameter is obtained, wherein the quantization index is used to represent an extreme value when the model-driven parameter is quantized; and,

[0014] quantizing the model driving parameter according to the quantization index of the model driving parameter to obtain a quantized value of the model driving parameter;

[0015] The three-dimensional hand model is driven by using the quantized value of the model driving parameter to obtain a smoothed three-dimensional hand model corresponding to the hand image.

[0016] According to a third aspect provided by an embodiment of the present invention, a computer storage medium is provided, wherein the computer storage medium stores a computer program, and the computer program is used to execute the method as described in the first aspect.

[0017] In the above-mentioned embodiment of the present application, multiple model driving parameters of the hand image are obtained, and for any one of the multiple model driving parameters, the quantization index of the model driving parameter is obtained based on the preset quantization step size and the minimum value corresponding to the model driving parameter, and the model driving parameter is quantized according to the quantization index of the model driving parameter to obtain the quantization value of the model driving parameter; the three-dimensional hand model is driven by the quantization value of the model driving parameter to obtain a smoothed three-dimensional hand model corresponding to the hand image. Therefore, in the embodiment of the present application, by mapping each model driving parameter of the hand image to a fixed quantization point respectively, the model driving parameters within the floating range of the same quantization interval are mapped to the same set of quantization values, thereby achieving the purpose of de-jittering and smoothing the model driving parameters and improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0019] Figure 1A schematic diagram of an application scenario of a smooth three-dimensional hand model provided by an embodiment of the present application is exemplarily shown;

[0020] Figure 2 The flowchart of the smoothing method of the three-dimensional hand model provided in the embodiment of the present application is exemplarily shown;

[0021] Figure 3 The schematic diagram of the process of determining the quantitative value of the model driving parameter provided by the embodiment of the present application is exemplarily shown;

[0022] Figure 4 A schematic diagram of a smoothed three-dimensional hand model provided by an embodiment of the present application is exemplarily shown;

[0023] Figure 5 The flowchart of determining the target quantization index of the hand image of the current frame provided by the embodiment of the present application is exemplarily shown;

[0024] Figure 6 The flowchart of the smoothing method of the three-dimensional hand model provided in the embodiment of the present application is exemplarily shown;

[0025] Figure 7 The schematic diagram of a smoothing device for a three-dimensional hand model provided in an embodiment of the present application is exemplarily shown;

[0026] Figure 8 The hardware structure diagram of the electronic device provided in the embodiment of the present application is exemplified. DETAILED DESCRIPTION

[0027] In order to make the purpose, implementation mode and advantages of the present application clearer, the exemplary implementation mode of the present application will be clearly and completely described below in conjunction with the drawings in the exemplary embodiments of the present application. Obviously, the described exemplary embodiments are only part of the embodiments of the present application, rather than all the embodiments.

[0028] Based on the exemplary embodiments described in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the claims attached to this application. In addition, although the disclosure in this application is introduced according to one or several exemplary examples, it should be understood that each aspect of the disclosure can also constitute a complete implementation method separately.

[0029] It should be noted that the brief description of terms in this application is only for the convenience of understanding the embodiments described below, and is not intended to limit the embodiments of this application. Unless otherwise specified, these terms should be understood according to their ordinary and common meanings.

[0030] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover but not exclude inclusion, for example, a product or device containing a series of components is not necessarily limited to those components clearly listed, but may include other components not clearly listed or inherent to these products or devices.

[0031] The term "module" as used in this application refers to any known or later developed hardware, software, firmware, artificial intelligence, fuzzy logic or combination of hardware and / or software code that is capable of performing the functions associated with that element.

[0032] The idea of ​​the embodiments of the present application is summarized below.

[0033] Based on the existing technology, there is a problem that jitter is easy to occur during the display of the three-dimensional hand model. The embodiment of the present application provides a smoothing method for a three-dimensional hand model, by obtaining multiple model driving parameters of a hand image, and for any one of the multiple model driving parameters, based on a preset quantization step and a minimum value corresponding to the model driving parameter, the quantization index of the model driving parameter is obtained, and the model driving parameter is quantized according to the quantization index of the model driving parameter to obtain the quantization value of the model driving parameter; the three-dimensional hand model is driven by the quantization value of the model driving parameter to obtain a smoothed three-dimensional hand model corresponding to the hand image. Therefore, in the embodiment of the present application, by mapping each model driving parameter of the hand image to a fixed quantization point respectively, the model driving parameters within the floating range of the same quantization interval are mapped to the same set of quantization values, thereby achieving the purpose of de-jittering and smoothing the model driving parameters, and improving the user experience. Below, the smoothing method of the three-dimensional hand model in the present application is described in detail in conjunction with the accompanying drawings.

[0034] like Figure 1As shown, it is a schematic diagram of another application scenario in an embodiment of the present application. The application scenario includes a VR device 110 and a memory 120. Among them, the VR device 110 obtains multiple model driving parameters of any hand image in the hand video stream from the memory 120, wherein the model driving parameters are used to drive a preset three-dimensional hand model, wherein the hand image includes a left hand image or a right hand image; and for any one of the multiple model driving parameters, based on a preset quantization step size and a minimum value corresponding to the model driving parameter, obtains a quantization index of the model driving parameter, wherein the quantization index is used to represent the extreme value when the model driving parameter is quantized; then the VR device 110 quantizes the model driving parameter according to the quantization index of the model driving parameter to obtain the quantization value of the model driving parameter; and uses the quantization value of the model driving parameter to drive the three-dimensional hand model to obtain a smoothed three-dimensional hand model corresponding to the hand image. And the smoothed three-dimensional hand model is displayed by the VR device 110.

[0035] Among them, the memory 120 and the VR device 110 in the embodiment of the present application can exchange information through a communication network, wherein the communication method adopted by the communication network can be divided into a wireless communication method or a wired communication method.

[0036] Exemplarily, the VR device 110 can access the network through cellular mobile communication technology to communicate with the storage 120, wherein the cellular mobile communication technology, for example, includes the fifth generation mobile communication (5th Generation Mobile Networks, 5G) technology.

[0037] Optionally, the VR device 110 can access the network via short-range wireless communication to communicate with the storage 120, wherein the short-range wireless communication method, for example, includes Wireless Fidelity (Wi-Fi) technology.

[0038] Among them, the description in this application only details a single VR device 110 and a single memory 120, but those skilled in the art should understand that the VR device 110 and the memory 120 shown are intended to represent the operation of the VR device 110 and the memory 120 involved in the technical solution of this application. It does not imply any limitation on the number, type or location of the VR device 110 and the memory 120. It should be noted that if additional modules are added to the illustrated environment or individual modules are removed from it, the underlying concept of the exemplary embodiment of this application will not be changed.

[0039] It should be noted that the smoothing method of the three-dimensional hand model proposed in this application is not only applicable to Figure 1 The application scenario shown is also applicable to any smooth device with a 3D hand model.

[0040] The following describes the smoothing method of the three-dimensional hand model in an exemplary embodiment of the present application in combination with the application scenarios described above and with reference to the accompanying drawings. It should be noted that the above application scenarios are only shown to facilitate understanding of the methods and principles of the present application, and the implementation methods of the present application are not limited in this regard.

[0041] like Figure 2 FIG. 1 is a flow chart of a smoothing method for a three-dimensional hand model, which may include the following steps:

[0042] Step 201: for any hand image in a hand video stream, a plurality of model driving parameters of the hand image are obtained, wherein the model driving parameters are used to drive a preset three-dimensional hand model, wherein the hand image includes a left hand image or a right hand image;

[0043] In order to facilitate the subsequent calculation of the quantized value of the model driving parameter, in one embodiment, before executing step 202, the minimum value of the model driving parameter is aligned with the quantization step length using the quantization step length to obtain the minimum value of the model driving parameter after alignment, and the aligned minimum value is updated as the minimum value of the model driving parameter. The minimum value of the model driving parameter after alignment can be determined in the following two ways:

[0044] Method 1: If the minimum value of the model driving parameter is less than the specified threshold, the minimum value in the model driving parameter is subtracted from the quantization step size to obtain a first intermediate value, and the first intermediate value is added to the target value to obtain the minimum value of the model driving parameter after alignment, wherein the target value is the remainder obtained by dividing the absolute value of the minimum value by the quantization step size. The minimum value of the model driving parameter after alignment can be obtained by formula (1):

[0045] min′ i =min i -S+abs(min i )%S......(1);

[0046] Among them, min′ i is the minimum value of the model-driven parameter i after alignment, min i is the minimum value of the model driving parameter i, and S is the quantization step size.

[0047] Method 2: If the minimum value of the model driving parameter is not less than the specified threshold, the minimum value of the model driving parameter is subtracted from the target value to obtain the minimum value of the model driving parameter after alignment. The minimum value of the model driving parameter after alignment can be obtained by formula (2):

[0048] min′ i =min i -abs(min i )%S......(2);

[0049] Step 202: for any one of the multiple model driving parameters, based on a preset quantization step size and a minimum value corresponding to the model driving parameter, obtaining a quantization index of the model driving parameter, wherein the quantization index is used to represent an extreme value when the model driving parameter is quantized;

[0050] The quantization index of the model driving parameter in the embodiment of the present application includes a quantization index upper limit and a quantization index lower limit. The following is an introduction to the method for determining the quantization index upper limit and the quantization index lower limit in the embodiment of the present application:

[0051] Quantization index upper limit: subtract the model driving parameter from the minimum value to obtain the parameter difference, and round up the quotient obtained by dividing the parameter difference by the quantization step size to obtain the quantization index upper limit. The quantization index upper limit can be obtained by formula (3):

[0052]

[0053] in, is the lower limit of the quantization index of the model driving parameter i.

[0054] Quantization index lower limit: The quotient obtained by dividing the parameter difference by the quantization step size is rounded down to obtain the quantization index lower limit. The quantization index lower limit can be obtained by formula (4):

[0055]

[0056] in, is the lower limit of the quantization index of the model driving parameter i.

[0057] The minimum values ​​corresponding to the model driving parameters in the embodiment of the present application are preset. The quantization step size and the minimum values ​​of the model driving parameters in the embodiment of the present application can be set according to the actual situation. The embodiment of the present application does not limit the quantization step size and the minimum values ​​of the model driving parameters.

[0058] Step 203: quantizing the model driving parameter according to the quantization index of the model driving parameter to obtain the quantization value of the model driving parameter;

[0059] like Figure 3 As shown, it is a schematic diagram of a process of determining the quantitative value of the model driving parameter, which may specifically include the following steps:

[0060] Step 301: obtaining target quantization indexes of a plurality of consecutive frames of hand images before the hand image, and counting the number of each target quantization index, wherein the target quantization index of any frame of hand image is obtained based on the quantization index of the hand image;

[0061] The number of frames of the multiple consecutive hand images preceding the hand image in the embodiment of the present application is preset and can be set according to actual conditions.

[0062] For example, if the number of frames of the multi-frame hand image is 4, and the current hand image is the 6th frame, the target quantization indexes of the 2nd to 5th frames of the hand image are obtained. If the target quantization index of the 1st frame of the hand image is a, the target quantization index of the 2nd frame of the hand image is b, the target quantization index of the 3rd frame of the hand image is c, the target quantization index of the 4th frame of the hand image is a, and the target quantization index of the 5th frame of the hand image is a. Then the number of target quantization indexes a is 3, the number of target quantization indexes b is 1, and the number of target quantization indexes c is 1. Then it is determined that the target quantization index a is the target quantization index with the largest number.

[0063] It should be noted that: in the embodiment of the present application, the target quantization index corresponding to each frame of the hand image is the upper limit or lower limit of the quantization index of the frame of the hand image. The specific method for determining the target quantization index is introduced below for the target quantization index of the current hand image.

[0064] Step 302: Compare the target quantization index with the quantization index lower limit of the model driving parameter to determine whether the target quantization index with the largest number is equal to the quantization index lower limit of the model driving parameter. If so, execute step 303; if not, execute step 304.

[0065] Step 303: Obtain the quantized value of the model driving parameter according to the quantization index lower limit, the minimum value of the model driving parameter and the quantization step size; wherein the quantized value of the model driving parameter can be obtained by (5):

[0066]

[0067] Among them, Q i is the quantitative value of the model driving parameter i, min i is the minimum value of the model driving parameter i, is the lower limit of the quantization index of the model driving parameter i, and S is the quantization step size.

[0068] Step 304: determine whether the target quantization index with the largest number is equal to the upper limit of the quantization index of the model driving parameter, if so, execute step 305, if not, execute step 306;

[0069] Step 305: Obtain the quantized value of the model-driven parameter according to the quantization index upper limit, the minimum value of the model-driven parameter and the quantization step size; wherein the quantized value of the model-driven parameter can be obtained by formula (6):

[0070]

[0071] in, is the upper limit of the quantization index of the model driving parameter i.

[0072] Step 306: Obtain the quantized value of the model driving parameter according to the quantized index lower limit, the target quantized index with the largest number, and the quantized step size. The quantized value of the model driving parameter can be obtained by formula (7):

[0073]

[0074] in, The index of the target with the largest number is quantized.

[0075] Step 204: Drive the three-dimensional hand model using the quantized value of the model driving parameter to obtain a smoothed three-dimensional hand model corresponding to the hand image.

[0076] like Figure 4 As shown in the figure, it can be seen that there is no jitter in the hand image after smoothing in the present application.

[0077] Next, the specific method for determining the target quantization index of the hand image is introduced. Since the method for determining the target quantization index of each frame of the hand image is the same, the present application takes the hand image of the current frame as an example to introduce the method for determining the target quantization index. Figure 5 As shown, it is a flowchart of a method for determining a target quantization index of a hand image of a current frame, comprising the following steps:

[0078] Step 501: compare the upper limit of the quantization index of the model driving parameter with the target quantization index with the largest number, and determine whether the upper limit of the quantization index of the model driving parameter is equal to the target quantization index with the largest number. If so, execute step 502; if not, execute step 503;

[0079] Step 502: Determine the upper limit of the quantization index as the target quantization index of the hand image of the current frame;

[0080] Step 503: Determine the lower limit of the quantization index as the target quantization index of the hand image of the current frame.

[0081] In order to further connect the methods in this application, such as Figure 6 FIG. 1 is a flow chart of a smoothing method for a three-dimensional hand model in the present application, which may include the following steps:

[0082] Step 601: for any hand image in a hand video stream, a plurality of model driving parameters of the hand image are obtained, wherein the model driving parameters are used to drive a preset three-dimensional hand model, wherein the hand image includes a left hand image or a right hand image;

[0083] Step 602: aligning the minimum value of the model driving parameter with the quantization step length using the quantization step length to obtain the aligned minimum value of the model driving parameter, and updating the aligned minimum value as the minimum value of the model driving parameter;

[0084] Step 603: subtract the model driving parameter from the minimum value to obtain a parameter difference, and round up the quotient obtained by dividing the parameter difference by the quantization step length to obtain the quantization index upper limit;

[0085] Step 604: round down the quotient obtained by dividing the parameter difference by the quantization step length to obtain the quantization index lower limit;

[0086] Step 605: obtaining target quantization indexes of a plurality of consecutive frames of hand images before the hand image, and counting the number of each target quantization index, wherein the target quantization index of any frame of hand image is obtained based on the quantization index of the hand image;

[0087] Step 606: Compare the target quantization index with the largest number with the quantization index lower limit of the model driving parameter to determine whether the target quantization index with the largest number is equal to the quantization index lower limit of the model driving parameter. If so, execute step 607; if not, execute step 608.

[0088] Step 607: Obtain the quantized value of the model driving parameter according to the quantization index lower limit, the minimum value of the model driving parameter and the quantization step size;

[0089] Step 608: Determine whether the target quantization index with the largest number is equal to the upper limit of the quantization index of the model driving parameter, if so, execute step 609, if not, execute step 610;

[0090] Step 609: Obtaining a quantized value of the model driving parameter according to the quantization index upper limit, the minimum value of the model driving parameter and the quantization step size;

[0091] Step 610: Obtain the quantized value of the model driving parameter according to the quantization index lower limit, the target quantization index with the largest number, and the quantization step size;

[0092] Step 611: driving the three-dimensional hand model using the quantized value of the model driving parameter to obtain a smoothed three-dimensional hand model corresponding to the hand image;

[0093] Step 612: Compare the upper limit of the quantization index of the model driving parameter with the largest number of target quantization indexes to determine whether the upper limit of the quantization index of the model driving parameter is equal to the largest number of target quantization indexes, if so, execute step 613, if not, execute step 614;

[0094] Step 613: Determine the upper limit of the quantization index as the target quantization index of the hand image of the current frame;

[0095] Step 614: Determine the lower limit of the quantization index as the target quantization index of the hand image of the current frame.

[0096] Based on the same inventive concept, the three-dimensional hand model smoothing method disclosed above can also be implemented by a three-dimensional hand model smoothing device. The effect of the three-dimensional hand model smoothing device is similar to that of the above method, which will not be repeated here.

[0097] Figure 7 The figure is a schematic diagram of the structure of a smoothing device for a three-dimensional hand model according to an embodiment of the present disclosure.

[0098] like Figure 7 As shown, the smoothing device 700 of the three-dimensional hand model of the present disclosure may include a model driving parameter acquisition module 710 , a parameter quantization index determination module 720 , a parameter quantization value determination module 730 and a model driving module 740 .

[0099] A model driving parameter acquisition module 710 is used to acquire a plurality of model driving parameters of any hand image in a hand video stream, wherein the model driving parameters are used to drive a preset three-dimensional hand model, wherein the hand image includes a left hand image or a right hand image;

[0100] A parameter quantization index determination module 720, configured to obtain a quantization index of any one of the plurality of model-driven parameters based on a preset quantization step size and a minimum value corresponding to the model-driven parameter, wherein the quantization index is used to represent an extreme value when the model-driven parameter is quantized;

[0101] A parameter quantization value determination module 730, configured to quantize the model driving parameter according to the quantization index of the model driving parameter to obtain the quantization value of the model driving parameter;

[0102] The model driving module 740 is used to drive the three-dimensional hand model using the quantized value of the model driving parameter to obtain a smoothed three-dimensional hand model corresponding to the hand image.

[0103] In one embodiment, the apparatus further comprises:

[0104] The parameter alignment module 750 is used to align the minimum value of the model driving parameter with the quantization step size based on the preset quantization step size and the minimum value corresponding to the model driving parameter before obtaining the quantization index of the model driving parameter, so as to obtain the aligned minimum value of the model driving parameter, and update the aligned minimum value to the minimum value of the model driving parameter.

[0105] In one embodiment, the parameter alignment module 750 is specifically configured to:

[0106] If the minimum value of the model driving parameter is less than a specified threshold, the minimum value in the model driving parameter is subtracted from the quantization step size to obtain a first intermediate value, and the first intermediate value is added to the target value to obtain the minimum value of the model driving parameter after alignment, wherein the target value is the remainder obtained by dividing the absolute value of the minimum value by the quantization step size; or,

[0107] If the minimum value of the model driving parameter is not less than the specified threshold, the minimum value of the model driving parameter is subtracted from the target value to obtain the minimum value of the model driving parameter after alignment.

[0108] In one embodiment, the quantization index of the model driving parameter includes a quantization index upper limit and a quantization index lower limit; the parameter quantization index determination module 720 is specifically used to:

[0109] Subtracting the model driving parameter from the minimum value to obtain a parameter difference, and rounding up the quotient obtained by dividing the parameter difference by the quantization step size to obtain the quantization index upper limit; and

[0110] The quotient obtained by dividing the parameter difference by the quantization step size is rounded down to obtain the quantization index lower limit.

[0111] In one embodiment, the parameter quantization index determination module 720 is specifically configured to:

[0112] The quantization index lower limit is obtained by the following formula:

[0113]

[0114] in, is the upper limit of the quantitative index of the model driving parameter i, C i is the model driving parameter i, min i is the minimum value of the model driving parameter i, and S is the quantization step size;

[0115] The quantization index upper limit is obtained by the following formula:

[0116]

[0117] in, is the lower limit of the quantization index of the model driving parameter i.

[0118] In one embodiment, the quantization index includes a quantization index upper limit and a quantization index lower limit;

[0119] The parameter quantization value determination module 730 is specifically used to:

[0120] Obtaining target quantization indexes of a plurality of consecutive frames of hand images before the hand image, and counting the number of each target quantization index, wherein the target quantization index of any frame of hand image is obtained based on the quantization index of the hand image;

[0121] If the largest number of target quantization indexes is equal to the lower limit of the quantization index of the model driving parameter, then according to the lower limit of the quantization index, the minimum value of the model driving parameter and the quantization step size, the quantization value of the model driving parameter is obtained; or,

[0122] If the largest number of target quantization indexes is equal to the upper limit of the quantization index of the model driving parameter, then according to the upper limit of the quantization index, the minimum value of the model driving parameter and the quantization step size, the quantization value of the model driving parameter is obtained; or,

[0123] If the target quantization index with the largest number is not equal to the upper limit of the quantization index of the model driving parameter, and is not equal to the lower limit of the quantization index of the model driving parameter, then the quantization value of the model driving parameter is obtained based on the lower limit of the quantization index, the target quantization index with the largest number and the quantization step.

[0124] In one embodiment, the parameter quantization value determination module 730 is specifically configured to:

[0125] The quantitative value of the model driving parameter is obtained by the following formula:

[0126]

[0127] Among them, Q i is the quantitative value of the model driving parameter i, min i is the minimum value of the model driving parameter i, is the lower limit of the quantization index of the model driving parameter i, and S is the quantization step size;

[0128] The quantitative value of the model driving parameter is obtained by the following formula:

[0129]

[0130] in, is the upper limit of the quantitative index of the model driving parameter i;

[0131] The quantitative value of the model driving parameter is obtained by the following formula:

[0132]

[0133] in, Tick ​​the target quantization index with the largest number.

[0134] In one embodiment, the apparatus further comprises:

[0135] A target quantization index determination module 760 is used to compare the quantization index upper limit of the model driving parameter with the largest number of target quantization indexes after obtaining the quantization index of the model driving parameter based on a preset quantization step size and a minimum value corresponding to the model driving parameter;

[0136] If the upper limit of the quantization index of the model driving parameter is equal to the largest number of target quantization indexes, then the upper limit of the quantization index is determined as the target quantization index of the hand image of the current frame; or

[0137] Otherwise, the quantization index lower limit is determined as the target quantization index of the hand image of the current frame.

[0138] After introducing a method and apparatus for smoothing a three-dimensional hand model according to an exemplary embodiment of the present invention, next, an electronic device according to another exemplary embodiment of the present invention is introduced.

[0139] It will be appreciated by those skilled in the art that various aspects of the present invention may be implemented as a system, method or program product. Therefore, various aspects of the present invention may be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to herein as a "circuit", "module" or "system".

[0140] In some possible implementations, the electronic device according to the present invention may include at least one processor and at least one computer storage medium. The computer storage medium stores program code, and when the program code is executed by the processor, the processor executes the steps of the method for smoothing a three-dimensional hand model according to various exemplary embodiments of the present invention described above in this specification. For example, the processor may execute the following steps: Figure 2 Steps 201-204 shown in .

[0141] Refer to the following Figure 8 An electronic device 800 according to this embodiment of the present invention will be described. Figure 8 The electronic device 800 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0142] like Figure 8 As shown, the electronic device 800 is in the form of a general electronic device. The components of the electronic device 800 may include but are not limited to: at least one processor 801, at least one computer storage medium 802, and a bus 803 connecting different system components (including the computer storage medium 802 and the processor 801).

[0143] Bus 803 represents one or more of several types of bus structures, including a computer storage media bus or computer storage media controller, a peripheral bus, a processor, or a local bus using any of a variety of bus architectures.

[0144] The computer storage medium 802 may include readable media in the form of volatile computer storage media, such as random access computer storage media (RAM) 821 and / or cache storage media 822 , and may further include read-only computer storage media (ROM) 823 .

[0145] The computer storage medium 802 may also include a program / utility 825 having a set (at least one) of program modules 824, such program modules 824 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0146] The electronic device 800 can also communicate with one or more external devices 804 (e.g., keyboards, pointing devices, etc.), can also communicate with one or more devices that enable users to interact with the electronic device 800, and / or communicate with any device (e.g., routers, modems, etc.) that enables the electronic device 800 to communicate with one or more other electronic devices. This communication can be carried out through an input / output (I / O) interface 805. In addition, the electronic device 800 can also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs) and / or public networks, such as the Internet) through a network adapter 806. As shown in the figure, the network adapter 806 communicates with other modules for the electronic device 800 through a bus 803. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the electronic device 800, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0147] In some possible implementations, various aspects of the three-dimensional hand model smoothing method provided by the present invention may also be implemented in the form of a program product, which includes program code. When the program product runs on a computer device, the program code is used to enable the computer device to execute the steps of the three-dimensional hand model smoothing method according to various exemplary embodiments of the present invention described above in this specification.

[0148] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A smoothing method for a three-dimensional hand model, characterized in that: The method comprises: For any hand image in the hand video stream, obtain a plurality of model driving parameters of the hand image, wherein the model driving parameters are used to drive a preset three-dimensional hand model, wherein the hand image includes a left hand image or a right hand image; For any one of the plurality of model-driven parameters, based on a preset quantization step size and a minimum value corresponding to the model-driven parameter, a quantization index of the model-driven parameter is obtained, wherein the quantization index is used to represent an extreme value when the model-driven parameter is quantized; and, quantizing the model driving parameter according to the quantization index of the model driving parameter to obtain a quantized value of the model driving parameter; The three-dimensional hand model is driven by using the quantized value of the model driving parameter to obtain a smoothed three-dimensional hand model corresponding to the hand image.

2. The method according to claim 1, characterized in that Before obtaining the quantization index of the model driving parameter based on the preset quantization step size and the minimum value corresponding to the model driving parameter, the method further includes: The minimum value of the model driving parameter is aligned with the quantization step size by using the quantization step size to obtain the aligned minimum value of the model driving parameter, and the aligned minimum value is updated as the minimum value of the model driving parameter.

3. The method according to claim 2, characterized in that The step of aligning the minimum value of the model driving parameter with the quantization step size by using the quantization step size to obtain the minimum value of the model driving parameter after alignment includes: If the minimum value of the model driving parameter is less than a specified threshold, the minimum value in the model driving parameter is subtracted from the quantization step size to obtain a first intermediate value, and the first intermediate value is added to the target value to obtain the minimum value of the model driving parameter after alignment, wherein the target value is the remainder obtained by dividing the absolute value of the minimum value by the quantization step size; or, If the minimum value of the model driving parameter is not less than the specified threshold, the minimum value of the model driving parameter is subtracted from the target value to obtain the minimum value of the model driving parameter after alignment.

4. The method according to claim 1, characterized in that: The quantization index of the model driving parameter includes a quantization index upper limit and a quantization index lower limit; The obtaining of the quantization index of the model driving parameter based on the preset quantization step size and the minimum value corresponding to the model driving parameter includes: Subtracting the model driving parameter from the minimum value to obtain a parameter difference, and rounding up the quotient obtained by dividing the parameter difference by the quantization step size to obtain the quantization index upper limit; and The quotient obtained by dividing the parameter difference by the quantization step size is rounded down to obtain the quantization index lower limit.

5. The method according to claim 4, characterized in that The quantization index lower limit is obtained by the following formula: in, is the upper limit of the quantitative index of the model driving parameter i, C i is the model driving parameter i, min i is the minimum value of the model driving parameter i, and S is the quantization step size; The quantization index upper limit is obtained by the following formula: in, is the lower limit of the quantization index of the model driving parameter i.

6. The method according to claim 1, characterized in that The quantization index includes a quantization index upper limit and a quantization index lower limit; The step of quantizing the model driving parameter according to the quantization index of the model driving parameter to obtain the quantized value of the model driving parameter includes: Obtaining target quantization indexes of a plurality of consecutive frames of hand images before the hand image, and counting the number of each target quantization index, wherein the target quantization index of any frame of hand image is obtained based on the quantization index of the hand image; If the largest number of target quantization indexes is equal to the lower limit of the quantization index of the model driving parameter, then according to the lower limit of the quantization index, the minimum value of the model driving parameter and the quantization step size, the quantization value of the model driving parameter is obtained; or, If the largest number of target quantization indexes is equal to the upper limit of the quantization index of the model driving parameter, then according to the upper limit of the quantization index, the minimum value of the model driving parameter and the quantization step size, the quantization value of the model driving parameter is obtained; or, If the target quantization index with the largest number is not equal to the upper limit of the quantization index of the model driving parameter, and is not equal to the lower limit of the quantization index of the model driving parameter, then the quantization value of the model driving parameter is obtained based on the lower limit of the quantization index, the target quantization index with the largest number and the quantization step.

7. The method according to claim 6, characterized in that The obtaining the quantized value of the model driving parameter according to the quantization index lower limit, the minimum value of the model driving parameter and the quantization step size includes: The quantitative value of the model driving parameter is obtained by the following formula: Among them, Q i is the quantitative value of the model driving parameter i, min i is the minimum value of the model driving parameter i, is the lower limit of the quantization index of the model driving parameter i, and S is the quantization step size; The obtaining the quantized value of the model driving parameter according to the maximum quantized value, the minimum value of the model driving parameter and the quantized step size comprises: The quantitative value of the model driving parameter is obtained by the following formula: in, is the upper limit of the quantitative index of the model driving parameter i; The obtaining, according to the quantization index lower limit, the largest number of target quantization indexes and the quantization step size, a quantization value of the model driving parameter includes: The quantitative value of the model driving parameter is obtained by the following formula: in, The index of the target with the largest number is quantized.

8. The method according to claim 6, characterized in that After obtaining the quantization index of the model driving parameter based on the preset quantization step size and the minimum value corresponding to the model driving parameter, the method further includes: Comparing the upper limit of the quantization index of the model driving parameter with the largest number of target quantization indexes; If the upper limit of the quantization index of the model driving parameter is equal to the target quantization index with the largest number, determining the upper limit of the quantization index as the target quantization index of the hand image of the current frame; Otherwise, the quantization index lower limit is determined as the target quantization index of the hand image of the current frame.

9. An electronic device, characterized in that: comprising a processor and a memory, wherein the processor and the memory are connected via a bus; The memory stores a computer program, and the processor is configured to perform the following operations based on the computer program: For any hand image in the hand video stream, obtain a plurality of model driving parameters of the hand image, wherein the model driving parameters are used to drive a preset three-dimensional hand model, wherein the hand image includes a left hand image or a right hand image; For any one of the plurality of model-driven parameters, based on a preset quantization step size and a minimum value corresponding to the model-driven parameter, a quantization index of the model-driven parameter is obtained, wherein the quantization index is used to represent an extreme value when the model-driven parameter is quantized; and, quantizing the model driving parameter according to the quantization index of the model driving parameter to obtain a quantized value of the model driving parameter; The three-dimensional hand model is driven by using the quantized value of the model driving parameter to obtain a smoothed three-dimensional hand model corresponding to the hand image.

10. The electronic device according to claim 9, characterized in that: The processor is further configured to: Before obtaining the quantization index of the model driving parameter based on the preset quantization step size and the minimum value corresponding to the model driving parameter, the minimum value of the model driving parameter is aligned with the quantization step size using the quantization step size to obtain the aligned minimum value of the model driving parameter, and the aligned minimum value is updated to the minimum value of the model driving parameter.

Images