CN114758044A - Three-dimensional clothing model manufacturing quality control method, equipment and storage medium - Google Patents

Abstract

The invention discloses a three-dimensional clothing model manufacturing quality control method, which comprises the following steps: (1) acquiring a two-dimensional image of a target garment; (2) performing preliminary inspection on the two-dimensional image according to a preset rule; (3) adjusting the two-dimensional image which does not meet the requirements according to a preset rule; (4) obtaining a two-dimensional clothing image which meets the manufacturing requirement of the three-dimensional clothing model; (5) making a three-dimensional clothing model according to the two-dimensional clothing image; (6) carrying out wiring optimization and model inspection on the three-dimensional garment model; (7) and generating a final three-dimensional clothing model file. The method keeps the manufacturing quality of the three-dimensional clothes model through a series of methods, fully considers the influence of all links on the quality in the manufacturing of the clothes model, sets full-process quality control measures and rules in advance, and the rules and the operation are simple and controllable, so that the processing speed is kept fast, and the overall quality of the clothes model is also kept.

Description

Three-dimensional clothing model manufacturing quality control method, equipment and storage medium

Technical Field

The invention belongs to the field of three-dimensional garment model manufacturing, and particularly relates to a method, equipment and a storage medium for performing full-flow control on three-dimensional garment model manufacturing quality during virtual reloading.

Background

With the development of internet technology, online shopping is more and more popular. Compared with shopping in a physical store, online shopping has the advantages of multiple commodity types, convenience in shopping and the like. However, there are some problems that are not easy to solve when purchasing commodities on the internet, and most importantly, the commodities to be purchased cannot be checked on the spot. The problem of clothing is most prominent in all commercial varieties. Compared with the method that the clothes effect can be changed and checked in real time in the shopping of a physical store, the online clothes shopping can not provide an effect picture aiming at a consumer, only can provide a picture of model fitting, and even has no fitting picture, so that the consumer can not intuitively obtain the matching degree of the clothes and the body figure of the consumer in real time. Resulting in a large amount of returns.

In response to this problem, operators have attempted to solve this problem by providing simulated fitting effects for consumers using virtual fitting techniques. Of course, there are other situations in reality where virtual fitting and changing techniques can be used, such as in network games. Therefore, this technology has been developed more rapidly.

The virtual fitting refers to a technical application that a user can view the 'changing' effect on a terminal screen in real time without actually changing clothes with the wearing effect. The existing dressing change technology mainly comprises a plane fitting technology and a three-dimensional virtual fitting technology. The former basically collects pictures of users, collects pictures of clothes, then stretches or compresses clothes into a state with the same size as the human body, and then cuts and splices the clothes to form an image after dressing, but the image has poor reality degree due to a simple and rough image processing mode, does not consider the actual body type of the users at all, and only carries the clothes to the pictures of the users, and can not meet the requirements of the users. The latter usually collects the three-dimensional information of the person through a three-dimensional collecting device and combines the characteristics of the clothes to synthesize, or manually inputs the body data information provided by the user, generates a virtual human body three-dimensional model mesh according to a certain rule, and then combines the mesh with the clothes chartlet. On the whole, the three-dimensional virtual fitting needs a large amount of data acquisition or three-dimensional data calculation, the hardware cost is high, and the three-dimensional virtual fitting is not easy to popularize among ordinary users.

With the development of cloud computing technology, artificial intelligence technology and intelligent terminal processing capacity, a two-dimensional virtual fitting technology is generated. Such techniques essentially comprise three steps: (1) processing the personal body information provided by the user to obtain a target human body model; (2) processing the clothing information to obtain a clothing model; (3) the human body model and the clothing model are fused together to generate a simulated figure of the clothing worn by a person.

Regarding point (1), in the general computer vision field, there are many initial starting points for human body modeling, which generally include three major categories, namely omni-directional scanning of a real human body by using a 3D scanning device, a three-dimensional reconstruction method based on multi-view depth-of-field photography, and a method of combining a given image with a human body model to realize three-dimensional reconstruction. The 3D scanning equipment is used for carrying out omnibearing scanning on a real human body to obtain the most accurate information, but the equipment is expensive usually and needs high cooperation of a human body model, and the whole processing process has high requirements on the processing equipment, so the equipment is generally applied to some professional fields; secondly, the multi-view three-dimensional reconstruction method needs to provide images with multiple overlapped views of a reconstructed human body and establish a space conversion relation among the images, multiple groups of cameras are used for shooting multiple images, a 3D model is spliced, the operation is relatively simplified, the calculation complexity is still high, and in most cases, only people participating in the scene can obtain multi-angle images. A model obtained by splicing the pictures taken by the depth camera in the multi-angle shooting method does not have body scale data and cannot provide a basis for 3D perception. And then, according to size parameter information of girth, width, thickness and the like of a human body section, a human body three-dimensional curve which is matched with the real human body shape can be directly generated, and a predicted human body model can be obtained.

In the prior art, methods for constructing a human body model generally have several types: (1) the method is based on regression, a human body model represented by voxels is reconstructed through a convolutional neural network, the algorithm firstly estimates the position of a main joint point of a human body according to an input picture, then in a given voxel grid with a specified size according to the position of a key point, and the shape of the reconstructed human body is described by the whole shape of the internally occupied voxels according to whether each unit voxel in the voxel grid is occupied or not; (2) the method comprises the steps of roughly marking simple human skeleton key points on an image, and then carrying out initial matching and fitting on a human model according to the rough key points to obtain the approximate shape of the human body. (3) Representing the human skeleton by 23 skeleton nodes, then representing the posture of the whole human body by the rotation of each skeleton node, simultaneously representing the shape of the human body by 6890 vertex positions, giving the positions of the skeleton nodes in the fitting process, and simultaneously fitting the parameters of the shape and the posture so as to reconstruct the three-dimensional human body; or the CNN model is used for predicting key points on the image, and then the SMPL model is adopted for fitting to obtain an initial human body model. And then, the shape parameters obtained by fitting are used for back and forth normalizing the bounding boxes of the individual body joints, one bounding box corresponds to each joint, and the bounding boxes are represented by axial length and radius. And finally, combining the initial model and the bounding box obtained by regression to obtain the three-dimensional human body reconstruction. The method has the problems of low modeling speed, insufficient modeling precision and strong dependence on the created body and posture database on the reconstruction effect.

For point (3), the common virtual fitting rooms in the current market are mainly focused on style collocation, and the natural attribute of collision between a virtual character and cloth of clothes is not intuitively simulated, so that the virtual fitting rooms still have great defects in the aspect of reality. At present, more and more manufacturers vividly express user postures by using virtual characters, simulate collision response and real-time rendering between clothes and cloth and a human body in real time to increase the adhesion degree of a virtual world and a real world, bring more clothes changing fun to virtual clothes fitting users and enable more people to enjoy the convenience brought by clothes purchasing.

For point (2), there are several different methods in the prior art of generating three-dimensional garment models. (a) At present, a traditional clothes three-dimensional model building method is based on a two-dimensional clothes cutting piece design and sewing method. Firstly, reading a three-dimensional human body model and a two-dimensional clothing pattern, then setting sewing information of the two-dimensional clothing pattern, then placing the two-dimensional clothing pattern around the three-dimensional human body, and finally, adopting a physical method to carry out sewing simulation of the three-dimensional clothing pattern to form the three-dimensional clothing model. Here, the clothing Pattern (Pattern) refers to clothing pieces designed by professional calculation according to the style and size requirements of clothing design, and is a planar expression of a three-dimensional garment. From the geometrical point of view, the two-dimensional clothing pattern is a closed polygon formed by straight lines and curved lines. The setting of the sewing information of the clothing pattern, namely how to sew the boundaries of the specified pattern together, is one of the important steps of the three-dimensional clothing simulation, and influences the efficiency and the user experience of the clothing simulation. This method requires a certain garment expertise to design the pattern, which is not a quality possessed by all users of the virtual fitting, and also requires manual designation of the stitching relationship between the patterns, which takes a lot of time to set. (b) Besides, another novel three-dimensional modeling method is based on hand drawing, and a simple clothing model can be generated through line information drawn by a user hand. However, this method requires professional personnel to perform hand drawing, has poor reproducibility and repeatability, requires a lot of time for users to perform detailed drawing of clothes, and is difficult to be popularized in electronic commerce on a large scale. Both of these approaches are more prone to innovative design of new garments than three-dimensional modeling of existing garments for sale. (c) And the other method is to comprehensively use an image processing technology and a graph simulation technology on the basis of obtaining the clothing picture information to finally generate a virtual three-dimensional clothing model. The method comprises the steps of obtaining the outline and the size of the garment in a picture through outline detection and classification, finding out edges and key points of the edges from the outline through a machine learning method, generating sewing information through the corresponding relation of the key points, and finally performing physical sewing simulation on the garment in a three-dimensional space to obtain the real effect of the garment worn on a human body.

Based on the internet technology and the characteristics of the network environment where the internet technology is located, the three-dimensional clothing model can be directly obtained from the clothing image which is simple and easy to obtain, the convenience is the best, a model maker does not need to take pictures on site, and can complete the making of the 3D model only through the 2D image, which is undoubtedly the mode which is most easily survived in the real market. However, the method also brings problems, which causes unstable quality of the output three-dimensional clothing model and affects subsequent changing or displaying links. Therefore, how to ensure that the three-dimensional garment model meeting the quality requirement is obtained by processing the two-dimensional garment information becomes an important link in the whole virtual change-over project.

The prior art discloses a fit evaluation method of three-dimensional clothes in a network environment, which comprises the following specific steps: the first step is as follows: establishing a virtual clothing model; placing the original garment in a human body scanner to acquire three-dimensional point cloud on the surface of the garment to obtain a three-dimensional garment model, wherein the three-dimensional garment model is formed by connecting triangular facets, and the density of triangular units is 5000 per garment; the second step is that: establishing a target human body model; carrying out three-dimensional human body scanning on a target human body by using a human body scanner to obtain a three-dimensional human body model, wherein the three-dimensional human body model is formed by connecting triangular facets, and the density of triangular units is 10000 per person; the third step: fitting clothes virtually; placing the three-dimensional garment model obtained in the first step around the three-dimensional human body model obtained in the second step, for lower clothing, enabling the crotch bottom point of the garment to coincide with the crotch bottom point of the human body, enabling the distance between the crotch bottom point and the crotch bottom point to be not more than 1cm, for upper clothing, enabling the left and right shoulder points of the garment to be aligned with the left and right shoulder points of the human body, enabling the distance between the left and right breast sharp points of the garment to be not more than 1cm, and for shoulder-free sling clothing, enabling the left and right breast sharp points of the garment to be aligned with the left and right breast sharp points of the human body model respectively, and enabling the distance between the left and right breast sharp points to be not more than 1 cm; if the penetration occurs between the discharged three-dimensional clothing model and the three-dimensional human body model, the algorithm is used for compensation: the fourth step: evaluating the fit; if the three-dimensional garment model and the three-dimensional human body model which are discharged in the third step are not penetrated, the garment curved surface can completely cover the corresponding three-dimensional human body surface, and the garment curved surface is considered to fit: and if the three-dimensional clothing model and the three-dimensional human body model which are arranged in the third step are penetrated. The method actually verifies whether the manufactured clothing model meets the requirements or not, does not intervene and improve the whole process of the generation of the clothing model, belongs to post evaluation, and does not improve the quality of the generated clothing model.

The prior art II discloses a paper pattern sewing information automatic setting method for three-dimensional clothing simulation, which comprises the following steps: 1) reading a three-dimensional human body model; 2) reading in a two-dimensional clothing pattern; 3) placing the two-dimensional clothing pattern around the three-dimensional human body model; 4) automatically identifying sewing information of the clothing pattern; 5) the incorrect sewing information is modified interactively to obtain the complete sewing information of the clothing pattern; the three-dimensional human body model in the step 1) can be represented by a triangular mesh curved surface or a quadrilateral mesh curved surface; the boundary of the two-dimensional clothing pattern in the step 2) is composed of straight lines and curves, and the two-dimensional clothing pattern can be directly designed by a two-dimensional design method or can be designed by a three-dimensional curved surface unfolding method; the method for automatically identifying the sewing information of the clothing pattern in the step 4) comprises the following steps: according to the characteristics and attributes of the stitching boundary, including side length similarity, curvature similarity, shortest distance, normal relativity, non-interference property, non-stitching boundary and stitching constraint, the rationality of the stitching line is checked by adopting a principle that the distance of the three-dimensional paper pattern boundary is preferred, the stitching boundary information of the paper pattern is automatically identified, specifically, for each paper pattern boundary, all boundaries which are possibly stitched are firstly found out according to the length and the curvature similarity of the paper pattern boundary, then the rationality check is carried out according to the normal relativity, self non-stitching property, non-interference property and stitching constraint characteristics, one boundary property of the shortest distance is found out from all potential reasonable stitching boundaries, and the boundary property is set as the stitching boundary. The method aims at the improvement of the link of stitching in the generation process of the model, more influence matters need to be considered in the practical operation, only aims at the improvement of the stitching effect, and does not realize the whole flow promotion of the three-dimensional model production.

Therefore, in the technical field of virtual fitting subdivision, a method for controlling the manufacturing quality of the garment model in the whole process of manufacturing the garment model does not exist.

Disclosure of Invention

Based on the above problems, the present invention provides a three-dimensional garment modeling quality control method, apparatus, and storage medium that overcome the above problems. By the method, the quality of the garment model can be simply improved, professional skill support is not needed, and the garment model can be manufactured by only general workers, so that the quality control efficiency is greatly improved.

The invention provides a three-dimensional clothing model manufacturing quality control method, which comprises the following steps: (1) acquiring a two-dimensional image of a target garment; (2) performing preliminary inspection on the two-dimensional image according to a preset rule; (3) adjusting the two-dimensional image which does not meet the requirements according to a preset rule; (4) obtaining a two-dimensional clothing image which meets the manufacturing requirement of the three-dimensional clothing model; (5) making a three-dimensional clothing model according to the two-dimensional clothing image; (6) carrying out wiring optimization and model inspection on the three-dimensional garment model; (7) and generating a final three-dimensional clothing model file.

Further, the two-dimensional images of the target garment are at least four, namely the front side, the back side, the side and the details.

Further, the items of the preliminary examination include whether the illumination is uniform or whether a distinct bright-dark switching interface exists.

Further, the items of the preliminary examination include that the picture pixels are at least above 800X800, and the area occupied by clothes is not less than 20% of the area of the picture.

Furthermore, the adjustment of the two-dimensional clothing image which does not meet the requirements comprises the adjustment of brightness enhancement, size cutting or detail enlargement, and the picture which cannot be adjusted is eliminated.

Further, the manufacturing of the three-dimensional garment model comprises the steps of carrying out plate pushing and unfolding and tiling UV operations on the two-dimensional garment image, manufacturing a corresponding map, and manually aligning the UV through a software tool.

Further, the route optimization operation includes operations of re-topological routing and vertex merging.

Further, the automatic script detection and inspection operation of the clothing model comprises: whether each layer of split is achieved in the multilayer clothing, whether four sides of the multilayer clothing are wrongly converted into triangular sides or not, whether degenerated triangles exist or not, whether the degenerated triangles have the same UV distribution or not, whether the model is provided with a self-penetrating model or not, and whether the model and the human body model penetrate mutually or not.

Furthermore, a computer-readable storage medium is provided, wherein a computer program is stored in the computer-readable storage medium, and when being executed by a processor, the computer program implements the method and steps described above.

An electronic device is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor and the communication interface are used for realizing mutual communication by the memory through the communication bus; a memory for storing a computer program; a processor for implementing the methods and steps described above when executing programs stored in the memory.

The invention has the beneficial effects that:

1. the manufacturing quality of the clothing model is obviously improved. At present, the existing methods for improving the quality of the clothing model all focus on the production link of the model, and the improvement of the algorithm accounts for the most part, so that the authenticity and the naturalness of the clothing model can be improved. However, the manufacturing of the garment model involves steps and links, such as selecting photos, trimming photos, manufacturing a three-dimensional model, optimizing the three-dimensional model, and the like, and the work performed by the user mainly completes the quality control of the whole process. The quality (reality and naturalness) of the generated model is enabled to reach a better degree through a series of operations and specifications from the beginning of selecting the photos to the inspection after the model is manufactured. The quality control method is accurate to each step, and has high practicability in the occasions of large-scale production of the clothing models, because the clothing styles of the clothing models are various, but the quality control method for the clothing models is not changed, and the method can be suitable for manufacturing the clothing models in large scale. In other words, a set of standard quality control operation flow is used, and the set of flow can be implemented on specific picture model attribute requirements and technical operation, so that the manufactured garment model is guaranteed in terms of procedures, and the serious defect that a garment library cannot be selected and changed is avoided.

2. The clothing model has good matching degree with the human body model. The fitting degree approximately comprises two contents, namely, the fitting property of the clothes model which naturally follows the state change of the human body is good; and secondly, the texture of the cloth of the clothes is high in reduction degree, and looks natural and real with the surrounding environment and the human body model as a whole. In the clothes changing procedure, a three-dimensional clothes model is usually worn on a three-dimensional standard human body model, body type parameters of the target human body model are input to obtain the target human body model, the three-dimensional clothes model is changed along with the change from the standard human body model to the body type of the target human body model, and if a series of preprocessing work is carried out, the clothes model can show good fitting performance in motion. In addition, the three-dimensional garment model is subjected to wiring optimization and model inspection, cloth simulation is adopted to simulate the cloth effect which is close to reality (certainly, the cloth effect can be different from the physical effect in reality), the main salient here is the high reduction degree of the cloth texture simulation, the simulation accuracy of cloth printing is included, and meanwhile, the wiring and cloth effects are optimized. And finally, the superposed defects of the multiple layers of clothes in the clothes model are checked and removed to ensure that obvious BUG does not appear in the clothes model entering the next procedure, and the clothes can be matched naturally.

3. The requirement on operators is simple. The invention sets a series of links capable of being operated, can generally write mature program scripts to finish the work such as quadrilateral surface judgment, and even if the links needing manual intervention exist, the operation is simple, and can be finished by common manufacturing or art designing personnel. In practice, a special designer is generally designated to be responsible for completing the whole set of operations, and in the series of operations, the change of the algorithm for generating the clothing model is not involved, and only the wiring optimization is carried out on the generated model; the adjustment of the content of the original photo is not involved, and only the photos meeting the basic requirements are simply screened; the process of generating the three-dimensional model of the two-dimensional clothing image is not changed, the operations of pushing a plate, unfolding and tiling UV and making a corresponding chartlet are not interfered, the UV is aligned manually through a software tool, and the result is corrected according to the preset rules so as to ensure the correct development of the subsequent procedures. Although the above works are distributed in each link, the operation difficulty is not large in practice, and the popularization and the application in the group are convenient.

The method keeps the manufacturing quality of the three-dimensional clothing model, the usability, the reality and the reduction degree, fully considers the influence of all links on the quality in the manufacturing of the clothing model, sets the full-flow quality control measures and rules in advance, and has simple and controllable rules and operation, thereby not only keeping the rapid processing speed, but also keeping the overall quality of the clothing model.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only some embodiments described in the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without any creative effort.

FIG. 1 is an overall process flow diagram of one embodiment;

FIG. 2 is a schematic diagram of a layout optimization and vertex merging;

FIG. 3 is a schematic view of a multi-layer garment overlap inspection;

FIG. 4 is a schematic diagram of the system of the present invention.

Detailed Description

Features and exemplary embodiments of various aspects of the present invention will be described in detail below, and in order to make objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not to be construed as limiting the invention. It will be apparent to one skilled in the art that the present invention may be practiced without some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the present invention by illustrating examples of the present invention.

It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of additional identical elements in the process, method, article, or apparatus that comprises the element.

The following describes in detail the quality control method provided by the embodiment of the present invention with reference to the drawings.

As shown in fig. 1, the invention discloses a three-dimensional clothing model manufacturing quality control method, which comprises the following steps: (1) acquiring a two-dimensional image of a target garment; (2) performing preliminary inspection on the two-dimensional image according to a preset rule; (3) adjusting the two-dimensional image which does not meet the requirements according to a preset rule; (4) obtaining a two-dimensional clothing image which meets the manufacturing requirement of the three-dimensional clothing model; (5) making a three-dimensional clothing model according to the two-dimensional clothing image; (6) carrying out wiring optimization and model inspection on the three-dimensional garment model; (7) and generating a final three-dimensional clothing model file.

The three-dimensional garment modeling quality control method generally comprises several steps. Firstly, screening and checking a two-dimensional image; secondly, optimizing the manufacturing process of the three-dimensional clothing model; and thirdly, optimizing and checking the obtained clothing model.

In the prior art of generating three-dimensional garment models, there are several different approaches. At present, a traditional clothes three-dimensional model building method is based on a two-dimensional clothes cutting piece design and sewing method. This method requires a certain garment expertise to design the template. The other novel three-dimensional modeling method is based on hand drawing, and a simple clothing model can be generated through line information drawn by a user hand. And the other method is to comprehensively use an image processing technology and a graph simulation technology on the basis of obtaining the clothing picture information to finally generate a virtual three-dimensional clothing model. The method comprises the steps of obtaining the outline and the size of the garment in a picture through outline detection and classification, finding out edges and key points of the edges from the outline through a machine learning method, generating sewing information through the corresponding relation of the key points, and finally performing physical sewing simulation on the garment in a three-dimensional space to obtain the real effect of the garment worn on a human body. Further, there are methods such as a mapping method and a mathematical model simulation method, and the present invention is not particularly limited to these methods.

The method is mainly carried out aiming at the first method, because the method is more traditional, the research is deeper in all aspects, a large number of improvement methods exist, the quality of the clothes model is easier to guarantee, and the link trend is very consistent with the basic idea of the full-flow control of the invention.

Further, the two-dimensional images of the target garment are at least four, namely the front side, the back side, the side and the details. Most of the clothes relate to different styles and fabrics, and the contents displayed by the views in several directions of the clothes are certainly different in the normal state, which requires that more clothes information is collected, so that a good foundation can be laid for the subsequent modeling process. In particular, the garment images obtained by people usually are worn on human bodies, so that the patterns and the cloth designs of various parts of the garment are not easy to determine through the size relationship and the projection relationship among the parts of the garment. Therefore, in order to restore the original appearance of the garment as much as possible, at least four pictures containing the target garment image are collected, and the four pictures comprise four parts, namely the front side, the back side, the side and the details, so that the style and the design of the garment to be made can be comprehensively reflected. The detail part is mainly the special design part of the clothing, such as the discontinuous change of the cloth or lines. Of course, from the viewpoint of production quality, the larger the number of two-dimensional photographs of the garment, the better, but after all, the present invention is not a professional garment design application as an application mainly serving entertainment and games, does not require a full reduction of the original appearance of the garment, and only needs no unacceptable distortion in the application program.

Further, the items of the preliminary check include whether the illumination is uniform or whether there is an obvious bright-dark switching interface.

The brightness refers to the brightness of the picture, the contrast refers to the difference between the brightness of the picture, and the saturation refers to the fullness of the color of the picture. Picture files are typically in RGB format, primarily for display. RGB is an abbreviation for three colors, where R refers to Red (Red), G to Green (Green), and B to Blue (Blue). Modern times color theory holds that all colors are a combination of three colors, red, green and blue. In a computer, each color is recorded by one Byte (Byte), and three bytes are used in an RGB picture file to record three colors of red, green and blue, respectively, so that the better picture file is 24-bit. Some picture files also support transparency, which can also be recorded in one byte, so that the picture files supporting transparency are 32-bit. When a byte is used to record a color, the byte may be considered a number, with a byte having 8 bits (bits), each bit representing a binary number having a value of 0 or 1, such that a binary number of 8 bits converted to a decimal number may represent a range from 0 to 255. The color values may represent shades of the color by numbers from 0 to 255. The color is darkest when the value is 0 and brightest when the value is 255. When the three color values of red, green and blue are all 0, the picture is black, and when the three color values of red, green and blue are all white, the picture is white, so that the change of the three color values of red, green and blue can combine 16,777,216 colors including black, white and gray.

A picture is made up of vertically and horizontally interleaved dots, one dot called a pixel. The number of transverse points and the number of longitudinal points form the resolution of the picture, the product of the transverse points and the longitudinal points is the number of pixels, and the number of the pixels can be used for measuring the resolution of the picture. When a picture is cut, the number of pixels of the picture is reduced, and the resolution is also reduced. Each color of each pixel on the picture can have a variation from 0 to 255, and the higher the value, the higher the brightness of the color, so when the brightness of a picture is changed, the value of each color of each pixel on the picture is actually changed at the same time, and the brightness of the picture is improved, that is, the value of each color of each pixel on the picture is inversely adjusted, so that the brightness of the picture is reduced. For each color value of each pixel on the picture, with 127 as a boundary, values less than 127 are dark, and values greater than 127 are light. If all color values of each pixel on the picture are decreased, which are less than 127, and all color values of each pixel on the picture are increased, which are greater than 127, we see an adjustment of the contrast of the picture, i.e. the darker the dark part of the picture, and the brighter the bright part of the picture. For the invention, the illumination is uniform and the judgment of the light and shade switching interface is simpler, as long as the main part of the clothes does not have obvious light and shade color blocks. For example, during the shooting process of the model, sunlight shines on clothes through some covering objects to form a clear bright-dark switching interface, which is generally not satisfactory, and is reflected in a brightness value, and the value difference of the brightness level can be set to be more than 30, 40, 50 or 60, so that the condition of uniform illumination is not met. In addition, or in some cases, the non-uniformity of the indoor lighting causes some area blocks with too large brightness difference on the service, which is also not satisfactory. Although some technical methods can be adopted to enhance the brightness of a dark block in the prior art, such enhancement is in the data processing category, which is likely to cause the quality degradation of the subsequent process.

Further, the items of the preliminary examination include that the picture pixels are at least above 800X800, and the area occupied by clothes is not less than 20% of the area of the picture. This is also to ensure the quality of the subsequent output, if the pixels are too low or the area of the garment is too small, a few effective image information remains after the separation and stripping of the extraneous content, which can cause many problems in the subsequent image processing. In post-mapping, the resolution of the mapped picture is usually required to be 2048 or higher.

Furthermore, the adjustment of the two-dimensional clothing image which does not meet the requirements comprises the adjustment of brightness enhancement, size cutting or detail enlargement, and pictures which cannot be adjusted are eliminated. For the reloading software, the sources of the photos are various, and the unified photo format, resolution, garment display position, garment area and the like can provide great support for the subsequent three-dimensional garment model making. Because the current mainstream garment model making process inevitably introduces the neural network model for assistance, and an input picture meeting a certain standard obviously more easily outputs a result with better truth degree in the neural network model. However, the adjustment operation is suitable for grasping the degree of simple intervention so as to facilitate the unified operation standard and actual operation of the designer. For example, when the brightness of the whole picture is low, the brightness can be automatically enhanced by software to show more details of the clothing. For another example, without a detail photo, several images of the interested detail parts can be manually selected and submitted as materials. Therefore, in the subsequent process, because the reference material is sufficient, a model with better quality can be generated, and the quality of the whole model production can be improved.

Further, the manufacturing of the three-dimensional garment model comprises the steps of carrying out plate pushing and unfolding and tiling UV operations on the two-dimensional garment image, manufacturing a corresponding map, and manually aligning the UV through a software tool. The wearer wants to feel comfortable. Due to individual differences, the height, weight and weight of people are different. This requires garments to fit different body types. When the clothes are made into patterns, one specification (generally the middle number) is selected to make the clothes with the patterns, so that the clothes with various specifications are required to be drawn out by scaling on the basis of the specification to meet the requirements of different body types of the wearer, and the process of making the various specifications of the patterns by scaling is called a clothes pushing plate and also called a clothes code-putting process. The method belongs to the traditional garment making process, and the garment model making in software is also a similar process, and the processes are not improved, but only the result is limited to a certain extent. The UV map is a planar representation of the 3D model surface for easy packaging of textures. The process of creating a UV map is called UV unfolding. U and V refer to horizontal and vertical axes of a 2D space because X, Y and Z have been used in a 3D space. Once the polygon mesh is created, the next step is to "unroll" it into a UV map. In addition, cloth textures are added to give the mesh life and make it look more realistic or real. However, there is no east-west like 3D textures, since they are always 2D images. This is the use of UV mapping as it is the process of converting a 3D mesh into 2D information so that a 2D texture can be wrapped around it. In our operation, the corresponding UV alignment can be done using PHOTOSHOP, which will lay a good foundation for the later completion of the garment model in the 3D modeling software.

Further, the route optimization operation includes operations of re-topology routing and vertex merging, see fig. 2. After the model and the chartlet are confirmed to be qualified, wiring optimization needs to be carried out on the three-dimensional clothes model, and the following points are mainly focused: (1) and (6) re-topology. Within 3D modeling, the concept of topology (topology) refers to the point-line-surface layout, structure, and old connection cases of polygonal network models. In most cases, the appearance and size of the same plane are the same, but the arrangement of the vertices, edges and planes in the same plane is usually different. And a model is created, if the model has a good topological structure, the model can be viewed cleanly and neatly outside the wiring line, the working efficiency of modeling can be improved to a great extent, and the model can be operated and modified more quickly and accurately. In the step, the wiring of the model is re-topological by using tools such as zbrush and the like, the vertex density is ensured to be uniform and consistent during topology, and the uniformly set standard clothing model wiring can be used as a standard, and the vertex density is consistent with the standard. When rewiring is carried out, the following points are required, including the removal of incomplete geometric bodies; removing the die penetrating part; removing the isolated vertex; overlapping faces are deleted. (2) And merging the vertexes. And manually or automatically aligning and merging the adjacent vertexes to complete vertex merging so that unreasonable boundary edges do not exist between the clothes patches. Vertex merging may generally be done using Maya.

Further, the garment model automation script detection checking operation comprises: whether each layer of split is achieved on the multi-layer garment, whether four side faces are converted into triangular faces by mistake, whether degenerated triangles exist, whether the degenerated triangles have the same UV distribution, whether the model is provided with a self-penetrating model, and whether the model and the human body model penetrate mutually. Referring to fig. 3, in the clothes model, due to the ubiquitous presence of multiple layers of clothes, a large amount of overlapping parts are generated in the taken clothes picture, which usually results in obvious errors once the clothes model moves, such as that a drooping skirt hem is changed into a transverse skirt hem and the like; furthermore, there may be cases where the design of the cloth of the garment is severely distorted, which is unacceptable because some cloth patterns are blocked. Therefore, in the model generation stage, it is required to check whether a clothes overlapping situation as shown in fig. 3 occurs. If the situation occurs, the model directly returns to the first procedure to carry out three-dimensional model manufacturing again, and if the three-dimensional model cannot be manufactured again, the three-dimensional model is directly eliminated. What we do at this step is simply to find the problem and abandon it as a three-dimensional garment model when the problem is not solved. Other inspections are mainly automatically carried out through programs, defects with large visual influence can be avoided, and rules are formulated according to special requirements of the clothes model for the changing project, such as selection of a quadrilateral surface and a triangular surface, and through research, the quadrilateral surface can reflect authenticity of the clothes model in a visual effect better than the triangular surface.

The three-dimensional garment model needs to be matched with a standard human body model, the general requirements are that the garment model matched with the standard human body model is matched with the human body model under a target posture in a cloth physical simulation mode based on the garment model matched with the standard human body model, and the naturalness and the reasonability of the garment are ensured. Some basic requirements are usually met, including but not limited to the following: a. completely attaching the template to the initial position of a standard mannequin without penetrating the template; b. the output is uniform four-sided; c. the UV of the model needs to be unfolded, tiled, compacted and aligned, and the tiling needs to be manually aligned by a PHOTOSHOP tool; d. performing over-vertex merging; e. the output model should be uniformly reduced, and the reference standard total surface number does not exceed 15w surfaces/set; f. the material is required to be adjusted in mainstream garment design software, 10 frames of animation are calculated to observe the cloth effect, the expectation is reached, and the material parameters are stored; g. the rendering material is required to be adjusted in mainstream design software, and one rendering is previewed, so that the lambert attribute of the material is reasonable.

Because the garment model which is made by the user needs to be worn on the human body model and then is checked and processed, the basic mannequins can be designed and modeled in advance according to a predetermined human body modeling method, and the three-dimensional garment model is sleeved on the standard human body model so as to achieve the effect which is adaptive to the subsequent work flow of the user.

The main working contents are as follows: and combining the mathematical model to construct a three-dimensional standard human body model, namely a basic mannequin. The SMPL human body model of Mapu can avoid surface distortion of a human body in the motion process, and can accurately depict the shapes of muscle stretching and contraction motions of the human body. In the method, beta and theta are input parameters, wherein beta represents 10 parameters of the human body with high and low fat and thin body, head-to-body ratio and the like, and theta represents 75 parameters of the whole motion pose and 24 joint relative angles of the human body. The beta parameter is ShapeBlendPose parameter, and can control the change of human body shape through 10 incremental templates, and specifically, the change of human body shape controlled by each parameter can be depicted through a dynamic graph. Through the continuous animation of the change of the parameters of the hyperthyroidism, the fact that the continuous change of each control human body form parameter can cause local and even integral linkage change of the human body model can be clearly seen, and in order to reflect the movement of human muscle tissues, the linear change of each parameter of the SMPL human body model can cause large-area grid change. Figuratively speaking, for example, when adjusting the parameter of β 1, the model may directly understand the parameter change of β 1 as the whole change of the body, and you may only want to adjust the proportion of the waist, but the model may force the fat and thin of the legs, chest and even hands to adjust together. Although the working mode can greatly simplify the working process and improve the efficiency, the project pursuing the modeling effect is really very inconvenient. Because the SMPL manikin culmination is a model which is trained by Western body pictures and measurement data and conforms to the western body type, the body shape change rule of the SMPL manikin culminates to the common change curve of the Western, and when the SMPL manikin culmination is applied to modeling of a manikin of an Asian, a plurality of problems can occur, such as the proportion of arms and legs, the proportion of waist and body, the proportion of neck, the length of legs and the length of arms. Through our research, the large difference exists in the aspects, and if the SMPL human body model is used in a hard way, the final generation effect cannot meet our requirements.

Therefore, the effect is improved by adopting a human body model self-made mode. The core of the method is that a human body blenshape base is built to realize accurate independent control of a human body. Preferably, the three-dimensional standard human body model (basic mannequin) is composed of 20 parameters of the physique base and 170 skeleton parameters. The plurality of bases form the whole human body model, and each shape base is independently controlled and changed by parameters without mutual influence. So-called accurate control, on the one hand has increased the parameter of control, does not continue to use ten beta control parameters of mapplet, and like this, the parameter that can adjust is except general fat thin, has still added the length of arm, the length of shank, the fat thin of waist, buttock and chest etc. has improved the parameter more than one time in the aspect of the bone parameter, has richened the scope that can adjust the parameter greatly, provides good basis for the design standard manikin that becomes more meticulous. The independent control means that each base is independently controlled, such as waist, legs, hands, head and the like, each skeleton can be independently adjusted in length and is independent from each other, and physical linkage is not generated, so that fine adjustment of the human body model can be better realized. The model is not easy to be large and thick, and can not be adjusted to the form satisfied by the designer. The existing model embodies a corresponding relation on the mathematical principle, and is actually equivalent to that the model is designed from two parts of artificial aesthetics and data statistical analysis, so that the model is generated according to the design rule of the model and is considered to be a correct model according with the body type of the Asian person, and the model is obviously different from a big data training model of the SMPL (human body model), so that the parameter transformation of the model is more interpretable, the local body change of the body model can be better represented, in addition, the change is based on the mathematical principle, the influence of all parameters is avoided, and the complete independence state is kept between arms and legs. In fact, such many different parameters are designed, so that the defect of training a human body model by big data can be avoided, the human body model is accurately controlled in more dimensions, the parameters are not limited to some indexes such as height and the like, and the modeling effect is greatly improved. Only on the premise of self-building a form base, the setting of such many independent control parameters has practical significance, and the two are not available for meeting the requirements of designers on the standard.

After the step of putting the three-dimensional garment model on the standard body model, a preliminary 3D body model is obtained, comprising the skeleton position and the mesh (mesh) of the body model with long short messages. This mannequin is usually in the initial standard posture of two arms flat, two legs differential, right side standing, i.e. we commonly speak as a T-pos, see FIG. 2. The three-dimensional clothing model is worn on a standard human body model, which is a conventional technology in the field, and the three-dimensional clothing model is not limited too much and can achieve the required effect.

The method of generating a three-dimensional body model including generating a garment model according to the embodiments of the present invention described in connection with fig. 1 to 3 may be implemented by a processing body model and an imaging device. Fig. 4 is a diagram illustrating a hardware structure 300 of an apparatus for processing a three-dimensional model according to an embodiment of the present invention.

The invention also discloses a computer readable storage medium, in which a computer program is stored, which computer program, when being executed by a processor, realizes the quality control method and steps as described above.

The electronic equipment comprises a processor, a communication interface, a memory and a communication bus, wherein the processor and the communication interface are used for realizing the communication between the processor and the memory through the communication bus; a memory for storing a computer program; a processor for implementing the quality control method and steps described above when executing the program stored in the memory.

As shown in fig. 4, the apparatus 300 for implementing the three-dimensional clothing model quality control method in this embodiment includes: the device comprises a processor 301, a memory 302, a communication interface 303 and a bus 310, wherein the processor 301, the memory 302 and the communication interface 303 are connected through the bus 310 and complete mutual communication.

In particular, the processor 301 may include a Central Processing Unit (CPU), or A Specific Integrated Circuit (ASIC), or may be configured as one or more integrated circuits implementing an embodiment of the present invention.

Memory 302 may include mass storage for data or instructions. By way of example, and not limitation, memory 302 may include an HDD, floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or a Universal Serial Bus (USB) drive or a combination of two or more of these. Memory 302 may include removable or non-removable (or fixed) media, where appropriate. The memory 302 may be internal or external to the human image processing apparatus 300, where appropriate. In a particular embodiment, the memory 302 is a non-volatile solid-state memory. In certain embodiments, memory 302 comprises Read Only Memory (ROM). Where appropriate, the ROM may be mask-programmed ROM, Programmable ROM (PROM), Erasable PROM (EPROM), Electrically Erasable PROM (EEPROM), Electrically Alterable ROM (EAROM), or flash memory or a combination of two or more of these.

The communication interface 303 is mainly used for implementing communication between modules, apparatuses, units and/or devices in the embodiment of the present invention.

Bus 310 includes hardware, software, or both to couple the components of device 300 to one another. By way of example, and not limitation, a bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hypertransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an infiniband interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a video electronics standards association local (VLB) bus, or other suitable bus or a combination of two or more of these. Bus 310 may include one or more buses, where appropriate. Although specific buses have been described and shown in the embodiments of the invention, any suitable buses or interconnects are contemplated by the invention.

That is, the apparatus 300 shown in fig. 4 may be implemented to include: a processor 301, a memory 302, a communication interface 303, and a bus 310. The processor 301, memory 302 and communication interface 303 are coupled by a bus 310 and communicate with each other. The memory 302 is used to store program code; the processor 301 executes a program corresponding to the executable program code by reading the executable program code stored in the memory 302 for executing the quality control method in any embodiment of the present invention, thereby implementing the quality control method and apparatus described in conjunction with fig. 1 to 3.

The embodiment of the invention also provides a computer storage medium, wherein the computer storage medium is stored with computer program instructions; the computer program instructions, when executed by a processor, implement a quality control method of an embodiment of the invention.

It is to be understood that the invention is not limited to the specific arrangements and instrumentality described above and shown in the drawings. A detailed description of known methods is omitted herein for the sake of brevity. In the above embodiments, several specific steps are described and shown as examples. However, the method processes of the present invention are not limited to the specific steps described and illustrated, and those skilled in the art can make various changes, modifications and additions or change the order between the steps after comprehending the spirit of the present invention.

The functional blocks shown in the above-described structural block diagrams may be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, it may be, for example, an electronic circuit, an Application Specific Integrated Circuit (ASIC), suitable firmware, plug-in, function card, or the like. When implemented in software, the elements of the invention are the programs or code segments used to perform the required tasks. The program or code segments may be stored in a machine-readable medium or transmitted by a data signal carried in a carrier wave over a transmission medium or a communication link. A "machine-readable medium" may include any medium that can store or transfer information. Examples of a machine-readable medium include electronic circuits, semiconductor memory devices, ROM, flash memory, Erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, Radio Frequency (RF) links, and so forth. The code segments may be downloaded via computer networks such as the internet, intranet, etc.

It should also be noted that the exemplary embodiments mentioned in this patent describe some methods or systems based on a series of steps or devices. However, the present invention is not limited to the order of the above-described steps, that is, the steps may be performed in the order mentioned in the embodiments, may be performed in an order different from the order in the embodiments, or may be performed simultaneously.

As described above, only the specific embodiments of the present invention are provided, and it can be clearly understood by those skilled in the art that, for convenience and simplicity of description, the specific working processes of the system, the module and the unit described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again. It should be understood that the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the present invention, and these modifications or substitutions should be covered within the scope of the present invention.

Claims (10)

1. A three-dimensional garment modeling quality control method, the method comprising:

1) acquiring a two-dimensional image of a target garment;

2) performing preliminary inspection on the two-dimensional image according to a preset rule;

3) adjusting the two-dimensional image which does not meet the requirements according to a preset rule;

4) obtaining a two-dimensional clothing image which meets the manufacturing requirement of the three-dimensional clothing model;

5) making a three-dimensional clothing model according to the two-dimensional clothing image;

6) carrying out wiring optimization and model inspection on the three-dimensional garment model;

7) and generating a final three-dimensional clothing model file.

2. The method of claim 1, wherein the two-dimensional images of the target garment are acquired in at least four images, front, back, side and detail.

3. The method of claim 1, wherein the items of the preliminary examination include whether the lighting is uniform or whether there is a distinct bright-dark interface.

4. The method of claim 1, wherein the items of preliminary examination include picture pixels at least above 800X800, and clothing occupies an area not less than 20% of the picture area.

5. The method of claim 1, wherein adjusting the unsatisfactory two-dimensional garment image comprises: the brightness is enhanced, cut in size or enlarged in detail, and the picture which can not be adjusted is eliminated.

6. The method of claim 1, wherein the making of the three-dimensional garment model includes performing a push and unfold lay-flat UV operation on the two-dimensional garment image and making a corresponding map, manually aligning the UV via a software tool.

7. The method of claim 1, wherein the route optimization operation comprises operations of re-topological routing and vertex merging.

8. The method of claim 1, wherein the garment model automation script detection checking operation comprises: whether each layer of split is achieved in the multilayer clothing, whether four sides of the multilayer clothing are wrongly converted into triangular sides or not, whether degenerated triangles exist or not, whether the degenerated triangles have the same UV distribution or not, whether the model is provided with a self-penetrating model or not, and whether the model and the human body model penetrate mutually or not.

9. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the method and steps of any one of claims 1 to 8.

10. The electronic equipment is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor and the communication interface are used for realizing the communication between the processor and the memory through the communication bus; a memory for storing a computer program; a processor for implementing the method and steps of any of claims 1-8 when executing a program stored in a memory.

Images