Device or system for processing image data of a manipulable physical model based on user input

Abstract

Device or system (10), comprising: - Means (11) for capturing and / or receiving image data, wherein the image data represent a physical model, in particular an architectural model, wherein the physical model has at least one manipulable part with at least one visual feature; - Means (12) for entering user input, - Means (13) for processing the image data, wherein the means are set up to process the image data based on the at least one visual feature and based on user input.

Description

[0001] The invention relates to the field of creating and visualizing models, in particular architectural models.

[0002] The creation and visualization of models plays a role in a wide variety of fields, such as product development and architecture. These days, such models are typically created and visualized exclusively digitally, for example, in the form of 3D renderings. Creating and visualizing such digital models, or adapting them to structural changes in the underlying designs, is generally time-consuming. Furthermore, it usually requires extensive knowledge of the modeling and rendering software used, and individuals lacking this knowledge are practically unable to create digital models or their associated visualizations, or to make changes to the models.

[0003] Against this background, the present invention aims to eliminate or reduce at least one of the disadvantages of the prior art described above.

[0004] According to a first teaching of the present invention, the above-mentioned problem is solved by a device or a system comprising: - Means for capturing and / or receiving image data, wherein the image data represent a physical model, in particular an architectural model, wherein the physical model has at least one manipulable part with at least one visual feature; - Means of entering user input, - Means for processing the image data, wherein the means are set up to process the image data based on the at least one visual feature and based on user input.

[0005] In the context of the invention, a physical model is understood to be a model that actually exists, i.e., it has a spatial and physical form. For example, the physical model can be a three-dimensional model. For example, the physical model can be a model of a product or an architectural model. For example, the physical model can be a model of a building, a model of a part of a building, a model of a city, a model of a district, a model of a settlement, or a model of part of a settlement.

[0006] According to the invention, the physical model comprises at least one manipulable part. In the context of the invention, a manipulable part is understood to be a part of the physical model that can be modified by a user. For example, the user can change the spatial-physical design of the manipulable part, such as its shape. For example, the user can change the visual appearance of the manipulable part, such as its color. Examples of manipulable parts of the physical model include buildings, building components, building surfaces, facades, groups of buildings, city districts, settlement areas, streets, parks, bodies of water, open spaces, usable areas, or a combination of the aforementioned elements.

[0007] According to the invention, the manipulable part of the physical model has at least one visual feature. In the context of the invention, a visual feature is understood to be a feature that is visually perceptible, whereby the term "visual perception" includes not only perception with the human eye but also detection using technical aids such as cameras, sensors, etc. For example, the at least one visual feature is a color of the manipulable part or a surface thereof. For example, the at least one visual feature is a pattern of the manipulable part or a surface thereof, such as a hatched pattern, a dotted pattern, etc. For example, the at least one visual feature is a structure of the manipulable part or a surface thereof.For example, at least one visual characteristic is a property of the manipulable part or a surface thereof.

[0008] According to the invention, the device or system comprises means for acquiring and / or receiving image data, wherein the image data represents the physical model. For example, the means for acquiring and / or receiving image data include a camera or an image sensor for acquiring the image data. The camera or image sensor is preferably variably positionable so that image data can be acquired that represents the physical model from different perspectives. For example, the means for acquiring and / or receiving image data include an interface for image data that represents the physical model. For example, the means for acquiring and / or receiving image data include a memory for reading image data that represents the physical model.

[0009] According to the invention, the device or system includes means for inputting user input. For example, the means for inputting user input include a keyboard, a mouse, a touchpad, a microphone with speech recognition, etc.

[0010] According to the invention, the device or system includes means for processing the image data. For example, the means for processing the image data include a computing unit configured to process the image data based on at least one visual feature and on user input. The computing unit can be, for example, a personal computer, a laptop, a smartphone, a tablet computer, etc.

[0011] Unlike the prior art, the device or system according to the invention makes it possible to create visualizations of models without having to create a corresponding digital model. Furthermore, changes can be made to the models without having to replicate these changes in the digital models. Instead, a physical model is created or modifications are made to a physical model, and then a corresponding visualization is created from it using the device or system according to the invention. This results in time savings, since the at least one manipulable part of the physical model can be formed, for example, from building blocks or modeling clay, allowing the manipulable part to be quickly designed or modified.Furthermore, the physical model can be more intuitively accessible than a corresponding digital model, and creating the model or making constructive changes requires little or no knowledge of modeling and rendering programs. Therefore, even people without such knowledge are able to create visualizations of models or make changes to the model and the resulting visualization.

[0012] The device or system according to the invention can be used, for example, as follows: After a user has designed or modified the at least one manipulable part of the physical model with the at least one visual feature, corresponding image data of the model are acquired and / or acquired using the means for acquiring and / or receiving image data. The user also provides user input using the means for entering user input. Subsequently, the image data is processed by the means for processing image data based on the at least one visual feature and based on the user input in order to generate a visualization of the physical model. For example, the user can specify in the user input that a particular visual feature of the at least one manipulable part should be visualized in a specific way.For example, the user can specify that buildings in the editable area, which have a certain color in the model, should be visualized as residential buildings. When editing the image data, the color of the buildings is recognized and visualized accordingly.

[0013] In a preferred embodiment, the means for inputting user input can include means for the user to specify an image. In this embodiment, the means for processing the image data can be configured to process the image data based on the image specified by the user input.

[0014] In a preferred embodiment, the user input defines the at least one visual feature and at least one processing instruction associated with that visual feature. In this embodiment, the means for processing the image data are configured to process the image data such that at least one section of the image data, corresponding to at least one part of the model that at least partially exhibits the at least one visual feature, is processed according to the associated processing instruction. The processing instruction can also specify degrees of freedom for processing the image data. This allows a user to specify individual requirements for visualizing the model, which are then taken into account when creating the visualization.

[0015] In a further preferred embodiment, the means for processing the image data are configured to process the image data in such a way that at least a section of the image data, corresponding to at least a part of the model that at least partially exhibits the at least one visual feature, is at least partially replaced by newly generated image data. This achieves a high degree of design freedom when creating the visualization.

[0016] In another preferred embodiment, the means for processing the image data are configured to process the image data using an artificial intelligence (AI) model. For example, the AI ​​model may have been trained with training data from real and / or virtual buildings, city districts, etc. AI models are particularly well suited for processing image data in connection with the invention because, on the one hand, they allow for the implementation of individual user specifications for visualizing the model—for example, by entering prompts—and, on the other hand, they enable a high level of detail and design freedom when creating the visualization.

[0017] In a further preferred embodiment, the device or system is configured to generate at least one prompt for the artificial intelligence model based on user input. This can be achieved, for example, by configuring the means for user input to input a prompt that is directly fed to the AI ​​model. Alternatively, the device or system can also be configured to modify the user input to generate a prompt for the artificial intelligence model, for example, using prompt engineering methods. By generating prompts, the AI ​​model can receive corresponding user instructions and incorporate them into the visualization. The prompts can be formulated in such a way that individual user requirements for the model's visualization are implemented as precisely as possible.On the other hand, the prompts can also be formulated in such a way that the AI ​​model is given certain freedoms in the visualization, thus achieving greater design freedom in creating the visualization.

[0018] In another preferred embodiment, the newly generated image data is generated using the artificial intelligence model. Referring to the preceding explanations, this results in a particularly high degree of design freedom when creating the visualization.

[0019] In another preferred embodiment, the device or system is configured to process the captured and / or received image data essentially in real time. This means that the time between capturing and / or receiving the image data and the completion of the image processing is no longer than a predetermined time interval. For example, the predetermined time interval is chosen to allow for live visualization, taking into account the technically necessary processing time. This technically necessary processing time may depend, among other things, on the computing power and the desired visualization quality.For example, the specified time interval is chosen to be less than 30 seconds, preferably less than 20 or less than 10 seconds, and most preferably less than 5 seconds, less than 2 seconds, less than 1 second, or less than 0.5 seconds. By configuring the device or system to process the captured and / or received image data essentially in real time, a live visualization of the physical model can be achieved.

[0020] In a further preferred embodiment, the device or system further comprises: Means of outputting and / or storing the processed image data. This allows the processed image data to be output for visualization or stored for later use. For example, means of outputting and / or storing the processed image data include a screen for displaying the processed image data. For example, means of outputting and / or storing the processed image data include a printer for printing the processed image data. For example, means of outputting and / or storing the processed image data include storage for storing the processed image data. For example, means of outputting and / or storing the processed image data include 3D glasses for viewing the processed image data.For example, the means for outputting and / or storing the processed image data include a projector with which at least part of the processed image data is projected onto an additional physical model that is identical to the physical model.

[0021] In a further preferred embodiment, the device or system further comprises: - Means for outputting and / or storing data that represents the physical model.

[0022] This allows for the digitization of the physical model, which can then be output or stored for later use. For example, the data could be 3D data of a virtual representation of the physical model. For example, the means for outputting and / or storing data representing the physical model could include a 3D printer for producing a representation of the physical model. For example, the means for outputting and / or storing data representing the physical model could include storage for the data.

[0023] In a further preferred embodiment, the device or system further comprises: - the physical model, and / or - Means for creating the physical model or the at least one manipulable part of the physical model, wherein the means are suitable and / or equipped to create the physical model or the at least one manipulable part of the physical model in such a way that the at least one manipulable part has at least one visual feature.

[0024] This allows the physical model to be created or modified by a user in an intuitive manner and subsequently visualized. For example, the means for creating the physical model or at least one manipulable part of the physical model may include building blocks or interlocking blocks. For example, the means for creating the physical model or at least one manipulable part of the physical model may include a molding compound or modeling clay. For example, the means for creating the physical model or at least one manipulable part of the physical model may include a 3D printer used to create elements of the physical model, in particular elements of the at least one manipulable part.

[0025] In another preferred embodiment, the model is an architectural model. The invention is particularly advantageous in connection with architectural models. In particular, time savings can be achieved in the design process for architectural models, as the effort required to create digital models is reduced. Furthermore, even individuals without extensive knowledge of corresponding modeling and visualization programs can create visualizations of architectural models. This can be especially advantageous in so-called participatory processes, where, for example, the design of a city district is to be developed with the participation of citizens.With the device or system according to the invention, citizens can create an architectural model, for example of the district to be designed, and furthermore create a high-quality visualization of this model, without requiring any knowledge of architectural modeling and visualization programs.

[0026] Further embodiments and advantages of the invention can be found in the following detailed description of some exemplary embodiments of the present invention, particularly in conjunction with the drawing. The drawing shows in Fig. 1 a schematic representation of a system according to an embodiment of the invention; Fig. 2 a schematic representation of means for processing the image data according to a preferred embodiment of the invention; Fig. 3a a representation of a physical architectural model; and Fig. 3b a representation of a visualization of the architectural model from Fig. 3a.

[0027] Fig. Figure 1 shows a schematic representation of a system 10 according to an embodiment of the invention. The system 10 comprises means 11 for acquiring and / or receiving image data, wherein the image data represent a physical model, in particular an architectural model, the physical model having at least one manipulable part with at least one visual feature. The means 11 are, by way of example, a camera 11.

[0028] Furthermore, the system includes 10 means for inputting user input. These means include, for example, a keyboard and a mouse.

[0029] Furthermore, the system comprises 10 means 13 for processing the image data, wherein the means 13 are configured to process the image data based on at least one visual feature and based on user input. The means 13 are, by way of example, a computer 13, which is configured to process the image data based on at least one visual feature and based on user input. The computer 13 is connected via appropriate data connections to the camera 11 and the means 12 for inputting user input.

[0030] In the Fig. In the preferred embodiment shown in Figure 1, the system 10 also comprises means 14 for outputting and / or storing the processed image data. The means 14 are, by way of example, a screen 14.

[0031] The in Fig. System 10, as shown, can be used as follows: An architectural model contains a color-coded design model made of building blocks, modeling clay, or 3D-printed objects. The surrounding urban context of the architectural model consists, for example, of a white solid or textured 3D-printed building model. A camera allows for flexible viewing of the model from various angles, including camera movements. A prompt describes the volume of the colored model, providing an AI model with the properties to be interpreted. The AI ​​model recognizes the volume and its contours. Multiple colors are possible.

[0032] Individual properties can be assigned to the colors. Green building blocks / areas, for example, can be transformed into green facades or parks. Blue or red colors can be assigned to different building functions. Yellow areas can be used to create busy streets, bike paths, or pedestrian walkways. The colors can be flexibly "prompted." The possibilities are virtually limitless. The images, generated in near real-time, can be saved, discarded, or output as a visualized image. They can also be compiled into a video.

[0033] The physical model is transformed very specifically using a camera and an AI model. This creates a low-threshold entry point into architectural development.

[0034] Fig. Figure 2 shows a schematic representation of means for processing the image data according to a preferred embodiment of the invention.

[0035] Fig. Figure 3a shows a representation of a physical architectural model 31, wherein the architectural model 31 has a manipulable part 32 with a visual feature. The visual feature here is, by way of example, that the manipulable part 32 has a different color compared to the rest of the architectural model 31.

[0036] Fig. Figure 3b shows a representation of a visualization of the physical architectural model from Fig. 3a. The visualization was created using a system according to the invention. As shown in Fig. As shown in Figure 3b, high-quality visualizations can be created. Knowledge of architectural modeling and visualization programs is not required.

Claims

[1] Device or system (10) comprising: - Means (11) for capturing and / or receiving image data, wherein the image data represent a physical model, in particular an architectural model, wherein the physical model has at least one manipulable part with at least one visual feature; - Means (12) for entering user input, - Means (13) for processing the image data, wherein the means are set up to process the image data based on the at least one visual feature and based on user input. [2] Device or system according to claim 1, wherein the user input defines the at least one visual feature and at least one processing instruction which is assigned to the at least one visual feature, wherein the means for processing the image data are set up to process the image data in such a way that at least one section of the image data, which corresponds to at least one part of the model which at least partially exhibits the at least one visual feature, is processed in accordance with the at least one associated processing instruction. [3] Device or system according to claim 1 or 2, wherein the means for processing the image data are configured to process the image data in such a way that at least one section of the image data, which corresponds to at least one part of the model which at least partially has the at least one visual feature, is at least partially replaced by newly generated image data. [4] Device or system according to any one of claims 1 to 3, wherein the means for processing the image data are configured to process the image data using an artificial intelligence model. [5] Device or system according to claim 4, wherein the device or system is configured to generate at least one prompt for the artificial intelligence model based on user input. [6] Device or system according to claims 3 and 4, wherein the newly generated image data are generated using the artificial intelligence model. [7] Device or system according to any one of claims 1 to 6, wherein the device or system is configured to process the recorded and / or received image data substantially in real time. [8] Device or system according to any one of claims 1 to 7, further comprising: - Means (14) for outputting and / or storing the processed image data. [9] Device or system according to any one of claims 1 to 8, further comprising: - Means for outputting and / or storing data that represents the physical model. [10] Device or system according to any one of claims 1 to 9, further comprising: - the physical model, and / or - Means for creating the physical model or the at least one manipulable part of the physical model, wherein the means are suitable and / or equipped to create the physical model or the at least one manipulable part of the physical model in such a way that the at least one manipulable part has at least one visual feature. [11] Device or system according to any one of claims 1 to 10, wherein the model is an architectural model.

Images