WO2019058266A1

WO2019058266A1 - A system and method for conversion of a floor plan to a 3d scene for creation & rendering of virtual reality architectural scenes, walk through videos and images

Info

Publication number: WO2019058266A1
Application number: PCT/IB2018/057200
Authority: WO
Inventors: Sobin VARGHESE THOMBRA
Original assignee: Individual
Current assignee: Individual
Priority date: 2017-09-21
Filing date: 2018-09-19
Publication date: 2019-03-28
Anticipated expiration: 2020-03-21

Abstract

The present invention relates to a system and a method for conversion of a floor plan to a 3D scene for rendering of virtual reality or walk through videos or images. The system comprises of, a user interface device (202) and a cloud platform (207). The cloud platform (207) includes an application server (208), an application program interface (API) (209), a work flow system (210), and digital assets and furniture library (211). The application server (208) includes a process engine (213). The process engine (213) can be configured to identify objects present in the floor plan and to generate 3D scenes based on the identified objects and to render 3D scene to video or virtual reality (VR) visualization by converting a floor plan into 3D scene in the interface device, for providing the VR visual or walk through videos or 2D renderings to a user (201).

Description

A SYSTEM AND METHOD FOR CONVERSION OF A FLOOR PLAN TO A

3D SCENE FOR CREATION & RENDERING OF VIRTUAL REALITY ARCHITECTURAL SCENES, WALK THROUGH VIDEOS AND IMAGES

FIELD OF INVENTION

[0001] The embodiment herein generally relates to the field of visualizing architectural features, furniture and interiors for an upcoming or existing building. More specifically, the invention provides a system and a method for conversion of a floor plan to a 3D scene for rendering of virtual reality, walk through videos and images/ 2D renderings in an interface device.

BACKGROUND AND PRIOR ART

[0002] Today, visualization of an upcoming house or for re-modeling purposes is done using floorplans, 3D renderings or 3D walkthroughs. However, the floor planprovides a drawing to scale that shows a flat 2 dimensional view of the building, from various perspectives, along with the relationships between rooms, spaces and other physical features at one level of a structure. Dimensions are usually drawn between the walls to specify room sizes and wall lengths. However, the user cannot intuitively visualize an upcoming home in actual scale for a given floor plan, as if they were actually present there, because it is based on the user's imagination on how the final outcome in actual scale will look like just by looking at a 2D floor-plan or a non- actual scale three dimensional (3D) rendering or walkthrough.

[0003] Current process of creation of 3D renderings and walkthroughs from floor- plans requires significant manual efforts and time required to generate the 3D scene which eventually leads to increased cost. Further, many of the final renderings are not of premium quality as it requires significant computing infrastructure to generate out very high quality visualization of the upcoming building or home. Moreover, a user or designer needs to be skilled in operating 3D modeling packages to be able to do this and has to model the entire structure of the house, choose the different interiors and furniture based on the look required, render out the entire scene and also program the interactivity required for navigation. So the designer has to be a skilled person in that art or have multiple skilled team members. Due to the skill, cost of manual labor, time required for the manual and rendering process, the barrier for creation of 3D scenes of upcoming or existing homes is eventually high.

[0004] Visualizing furniture designs that are available in the stores in context to the buyer's home is a challenge. Buyers cannot visualize how the furniture will look like in actual scale in the upcoming or existing home or any commercial building, prior to purchase and many times they realize that the furniture does not fit well physically and aesthetically when actually placed at the venue. Even if a buyer has the floorplan for the house, it is not easy to visualize the store available furniture based on this floorplan, as many interior design packages use standard furniture models and not actual replicas of the store available furniture. Getting a visualization done by hiring 3D modelers is generally not economically attractive due to the cost of manual efforts , especially for small to mid-value purchases.

[0005] Therefore, there is a need to develop a system and a method for creating 3D scenes and subsequent rendering as Virtual Reality (VR), walkthrough videos or plain 2D images automatically that would help reduce the cost and efforts of visualization and increase adoption by making better visualization economically feasible.

OBJECTS OF THE INVENTION

[0006] Some of the objects of the present disclosure are described herein below: [0007] A main object of the present invention is to provide a system for conversion of a floor plan to a 3D scene for rendering of virtual reality, walk through videos and images in an interface device.

[0008] Another object of the present invention is to provide a system for displaying a floor plan in a 3D VR visualization to the user to customize the attributes of the object and furniture; wherein the conversion of the floor plan to a 3D scene for rendering of virtual reality, walk through videos and images in an interface device floor plan can be 2D or 3D floor plan or a vertical orthographic projection of a building.

[0009] Still another object of the present invention is to provide a system to generate the 3D scene from the floor plan by the user.

[00010] Yet another object of the present invention is to provide a system to customize the objects present in the 3D VR visualization.

[00011] Another object of the present invention is to provide a system for customizing using digital assets library in the 3D VR visualization.

[00012] Another object of the present invention is to provide a system for accessing furniture designs from online stores for implementing the new designs in the VR visualization.

[00013] The other objects and advantages of the present invention will be apparent from the following description when read in conjunction with the accompanying drawings, which are incorporated for illustration of preferred embodiments of the present invention and are not intended to limit the scope thereof.

SUMMARY OF THE INVENTION

[00014] In view of the foregoing, an embodiment herein provides a system and a method for conversion of a floor plan to a 3D scene for rendering of virtual reality or walk through videos or images. The system comprises of, a user interface device and at least a cloud platform. The cloud platform includes an application server, an application program interface (API), a work flow system, and digital assets and furniture library. The user interface device may include but not limited to a floor plan upload unit, a customization unit, a content downloader unit and a virtual reality (VR) , image and walkthrough viewer unit. The application server includes a process engine. Further, the process engine can be configured to identify objects present in the floor plan and to generate 3D scenes based on the identified objects and to render 3D scene to video or virtual reality (VR) visualization by converting a floor plan into 3D scene in the interface device, for providing the VR visual or walk through videos or 2D renderings to a user.

[00015] According to an embodiment, the floor plan upload unit can be configured for uploading floor plans into the system. The floor plan is a 2D floor plan or 3D floor plan or a vertical orthographic projection of a building or a location and so on. The customization unit can be configured for changing attributes of the objects present in the floor plan and also for adding new objects in the 3D scene using the interface device. The content downloader unit can be configured for allowing the user to download the rendered VR or walkthrough videos or images in a required format from the cloud platform using the user interface. The VR, image and walkthrough viewer unit can be configured for allowing the user to view visualization of the upcoming home or building or interiors of the given floor plan to provide the user a virtual and augmented reality experience in the user interface device using the rendered VR scene or walkthrough video or images.

[00016] According to an embodiment, the process engine may include but not limited to an image preprocessor module, a multi pass floor plan objects identifier module, a view and level merge module, a world scene builder module, a customization module, a 3D scene generator module, a rendering module and a package module. The rendering module may include sub-modules for output option that includes but not limited to a VR scene generator module, a video encoder module, images output module.

[00017] According to an embodiment, the multi pass floor plan objects identifier module comprises of sub modules to identify the objects in the floor plan. The sub modules may include but is not limited to a scale & orientation calibration module, a deep learning module, a floor plan symbols linear Support Vector Machine (SVM) classifier module, a training updater module, a wall detection module, an object filter module, a room identification module, a dimension detection module, a decision module and so on.

[00018] According to an embodiment, a method for conversion of a floor plan to a 3D scene for rendering of virtual reality, walk through videos and images. The method comprising the steps of, obtaining a floor plan along with a customization setting from a user interface device to a system, recognizing different symbols using advanced computer vision and deep learning technologies for determining the walls, rooms, furniture used and its positions in the floor plan, creating view and level merge for the exterior view of the house by taking the plan views & the elevation view inside the floor plan, generating 3D scene by taking into account the customization settings and selected digital assets from the digital assets library and rendering generated 3D scene into VR scene or walkthrough videos or images.

[00019] These and other aspects of the embodiments herein will be better appreciated and understood when considered in conjunction with the following description and the accompanying drawings. It should be understood, however, that the following descriptions, while indicating preferred embodiments and numerous specific details thereof, are given by way of illustration and not of limitation. Many changes and modifications may be made within the scope of the embodiments herein without departing from the spirit thereof, and the embodiments herein include all such modifications.

BRIEF DESCRIPTION OF DRAWINGS

[00020] The detailed description is set forth with reference to the accompanying figures. In the figures, the left-most digit(s) of a reference number identifies the figure in which the reference number first appears. The use of the same reference numbers in different figures indicates similar or identical items.

[00021] Fig. l illustrates the general block diagram of a system for conversion of a floor plan to a 3D scene for rendering of virtual reality, walk through videos and images, according to an embodiment herein;

[00022] Fig.2 illustrates the general architecture of the system for conversion of a floor plan to a 3D scene for rendering of virtual reality, walk through videos and images, according to an embodiment herein;

[00023] Fig.3 illustrates the schematic diagram of the process engine, according to an embodiment herein;

[00024] Fig.4 illustrates the schematic diagram of the multi pass floor plan objects identifier module, according to an embodiment herein; and

[00025] Fig.5 illustrates the method involved in the system for conversion of a floor plan to a 3D scene for rendering of virtual reality, walk through videos and images, according to an embodiment herein.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[00026] The embodiments herein and the various features and advantageous details thereof are explained more fully with reference to the non-limiting embodiments and detailed in the following description. Descriptions of well-known components and processing techniques are omitted so as to not unnecessarily obscure the embodiments herein. The examples used herein are intended merely to facilitate an understanding of ways in which the embodiments herein may be practiced and to further enable those of skill in the art to practice the embodiments herein. Accordingly, the examples should not be construed as limiting the scope of the embodiments herein.

[00027] As mentioned above, there is a need to develop a system and a method creating 3D scenes and subsequent rendering as Virtual Reality (VR), walkthrough videos or plain 2D images automatically. Further, there is a need to develop a system and a method for displaying the floor plan in a 3D VR visualization or images or walkthrough videos to a user along with a customization option. The embodiments herein achieve this by providing a system and a method for conversion of a floor plan to a 3D scene for automatically rendering of virtual reality or walk through videos or images. Referring now to the drawings, and more particularly to FIGS. 1 through 5, where similar reference characters denote corresponding features consistently throughout the figures, there are shown preferred embodiments.

[00028] Fig. l illustrates the general block diagram 100 of a system for conversion of a floor plan to a 3D scene for rendering of virtual reality, walk through videos and images, according to an embodiment. The general diagram for a system comprises of objects detector 102, a 3D scene generator 103, a digital assets and furniture library 105, and a rendering unit 104. The system works in a cloud based network. Initially, the cloud based system can take the floor plans along with customization settings or configuration 101 as input. The object detector utilizes the customization setting for recognizing different symbols using advanced computer vision. Further, the object detector utilizes deep learning technologies for determining the walls, rooms, furniture used and its positions. This is then converted to a 3D scene using the 3D scene generator 103 taking into account the customization settings and selected digital assets from the digital assets and furniture library 105. The generated 3D scene is then rendered using rendering unit 104 to generate VR scenes or walkthrough videos or images 106.

[00029] Fig.2 illustrates the general architecture 200 of the system for conversion of a floor plan to a 3D scene for rendering of virtual reality, walk through videos and images, according to an embodiment. The system for conversion of a floor plan to a 3D scene for rendering of virtual reality or walk through videos or images. The system comprises of, a user interface device 202 and a cloud platform 207. The cloud platform 207 includes an application server 208, an application program interface (API) 209, a work flow system 210, and digital assets & furniture library.

[00030] According to an embodiment, the API 209 can provide an interface to allow third party applications to communicate with the system.

[00031] According to an embodiment, the work flow system 210 can perform the sequence of task according to the process flow incorporated in the system and also monitors the sequence of tasks.

[00032] According to an embodiment, the user interface device includes but is not limited to smartphone, mobile phone, tablet, I-phone, I-pad and so on.

[00033] According to an embodiment, the user interface device 202 may include but not limited to a floor plan upload unit 203, a customization unit 204, a content downloader unit 205 and a virtual reality (VR), image and walkthrough viewer unit 206. The application server 208 includes a process engine 213. Further, the process engine 213 can be configured to identify objects present in the floor plan and to generate 3D scenes based on the identified objects and to render 3D scene to video or virtual reality (VR) visualization by converting a floor plan into 3D scene in the interface device, for providing the VR visual or walk through videos or 2D renderings to a user 201. [00034] According to an embodiment, the floor plan upload unit 203 can be configured for uploading floor plans into the system. The floor plan is a 2D floor plan or 3D floor plan or a vertical orthographic projection of a building and so on. The customization unit 204 can be configured for changing attributes of the objects present in the floor plan and also for adding new objects and/orspecific type of furniture from a database of available furniture into the 3D scene using the interface device. The content downloader unit 205 can be configured for allowing the user 201 to download the rendered VR or walkthrough videos or images 106 in a required format from the cloud platform 207 using the user interface device 202. The virtual reality (VR) , image and walkthrough viewer unit 206 can be configured for allowing the user 201 to view visualization of the floor plan as a home or interiors to provide the user 201 a virtual and augmented reality experience in the user interface device 202 using the rendered VR scene or walkthrough video or images 106.

[00035] According to an embodiment, the system allows the user 201 to upload the floor plan using the floor plan upload unit 203 and the customization settings 101 also uploaded in the customization unit 204 by the user 201 using the interface device 202. The uploaded content is transferred to the cloud platform 207. From the application server 208 the content is transferred to a processing unit that is a hyper reality engine 213. The process engine 213 can perform the operation of image pre-processing, multi pass floor plan objects identification, view and level merge process. Before generating the 3D scene, the process engine 213 utilizes the digital assets and furniture library to build the customized world scene. The process engine 213 accesses the library via a network line to customization unit 214. After that, the system can generate a 3D scene using the generated world scene. Then the generated 3D scene can be rendered as a VR scene. Further, the rendering can be done as a video or images or VR scene according to the user's requirement. The rendered 3D scene can be transferred for packaging in specific format and transfer that to the digital assets and furniture library 105 via a to package network 215. From the digital assets and furniture library 105, the system allows the user to download 205 the packaged content. Further, the system allows the user to view the content in the specific format using the VR viewer 206 present in the user interface device 202.

[00036] Fig.3 illustrates the schematic diagram 300 of the process engine 213, according to an embodiment. The schematic diagram of the process engine 213 comprises of modules but not limited to an image preprocessor module 301, a multi pass floor plan objects identifier module 302, a view and level merge module 303, a world scene builder module 304, a customization module 305, a 3D scene generator module 306, a rendering module 307 and a package module 311. The rendering module 307 may include sub-modules for output option that includes but not limited to a VR scene generator module 310, a video encoder module 309, and an images output module 308.

[00037] According to an embodiment, the image preprocessor module 301 can be configured for aiding object recognition by removing noise, isolating walls & furniture symbols, identifying region of interest, and handling colored & shaded floor plans using computer vision techniques and also configured to utilize computer vision techniques to aid object recognition. The multi pass floor plan objects identifier module 302 can be configured for identifying symbols such as walls, rooms in the floor plan using a trained and an untrained machine learning techniques to generate 3D scenes. There are several steps involved in the multi pass floor plan objects identifier module 302. Each step is performed using a sub module and that is elaborated in Fig.4.

[00038] According to an embodiment, the view and level merge module 303 can be configured for creating an exterior view of the house by taking the floor plan views & an elevation view inside the floor plan and for specifying the height of the walls, position & dimensions of the windows and doors, slope of the roofs, roof styles and so on. Further, the floor plan for a house can consist of several floors or levels that need to be merged into a single house. Each floor plan can be iterated through the system and then finally can be merged together. The world scene builder module 304 can be configured for generate coordinate positions based on world coordinates for a 3D scene and creating type of 3D object based on objects identified in the multi pass floor plan objects identifier module 302.

[00039] According to an embodiment, the customization module 305 can be configured for recognizing different symbols from an input of customization settings in the application server 208. The 3D scene generator module 306 can be configured for creating actual 3D scene using API 209 of external third-party modeling tools based on the inputs from the world space builder. The 3D models, textures, color of the walls, ceiling trims can be obtained from the digital asset library based on the customization settings specified by the user 201. The rendering module 307 can be configured for generating renders from the 3D scene by spawning render instances on the cloud platform 207. The render output depends on an output option selected by a user 201. The package module 311 can be configured for compressing the renders to easier download.

[00040] According to an embodiment, the VR scene generator module 310 can be configured for generating VR renders from the 3D scene by spawning render instances on the cloud platform 207. For example, if the user 201 selects the output option as a VR scene, then the VR scene generator module can generate VR renders from the 3D scene. Thevideo encoder module 309 can be configured for encoding video renders from the 3D scene by spawning render instances on the cloud platform 207. For example, if the user 201 selects the output option as a walkthrough video, then the video encoder module can generate walkthrough video from the 3D scene. The images output module 308 can be configured for generating image renders from the 3D scene by spawning render instances on the cloud platform 207. For example, if the user 201 selects the output option as images then the image output module can generate images from the 3D scene.

[00041] Fig.4 illustrates the schematic diagram 400 of the multi pass floor plan objects identifier module 302, according to an embodiment. The multi pass floor plan objects identifier module 302 comprises of sub modules to identify the objects in the floor plan. The sub modules may include but is not limited to a scale & orientation calibration module 401, a deep learning module 403, a floor plan symbols linear Support Vector Machine (SVM) classifier module 402, a training updater module 404, a wall detection module 405, an object filter module 406, a room identification module 407, a dimension detection module 408, a decision module 409 and other module 410.

[00042] According to an embodiment,the scale & orientation calibration module 401 can be configured for handling scale and orientation for symbol detection. The deep learning module 403 can be configured for utilizing unsupervised deep learning for detecting the symbols. The floor plan symbols linear Support Vector Machine (SVM) classifier module 402 can be configured for quickly identifying the symbols used in the floor plan using a trained linear SVM classifier based detection unit. The training for each type of symbol is done on a training dataset that is then used for recognition.The training updater module 404 can be configured for adding any unidentified symbol to the positive training database and adding incorrectly identified objects to the negative training dataset. The training updater module 404 can be further configured for retaining the linear SVM classifier using an updated training dataset that includes the positive training database and negative training database.

[00043] According to an embodiment,thewall detection module 405 can be configured for creating a structure of the house by identifying line segments on the floor plan. The object filter module 406 can be configured for removing identified symbols from the floor plan to ease and increase accuracy of the objects recognition.The room identification module 407 can be configured for identifying rooms by taking connected walls into account. The dimension detection module 408 can be configured for identifying dimensions and set the length and width of the walls accordingly using text recognition.The decision module 409 configured for conforming recognized symbols by taking into account the inputs from the linear SVM classifier, deep learning classifier and the room context.

[00044] Exemplary methods for conversion of a floor plan to a 3D scene for rendering of virtual reality, walk through videos and images are described with reference to Fig 5. These exemplary methods can be described in the general context of computer executable instructions. Generally, computer executable instructions can include routines, programs, objects, components, data structures, procedures, modules, functions, and the like, that perform particular function or implement particular abstract data types. The methods can also be practiced in a distributed computing environment where functions are performed by remote processing devices that are linked through a communication network. In a distributed computing environment, computer executable instructions may be located both in local and remote computer storage media, including memory storage devices.

[00045] The exemplary methods are illustrated as a collection of operations in a logical flow graph representing a sequence of operations that can be implemented in hardware, software, firmware, or a combination thereof. The order in which the methods are described is not intended to be construed as a limitation, and any number of the described method blocks can be combined in any order to implement the methods, or alternate methods. Additionally, individual operations may be deleted from the methods without departing from the spirit and scope of the subject matter described herein. In the context of software, the operations represent computer instructions that, when executed by one or more processors, perform the recited operations.

[00046] Fig.5 illustrates the method 500 involved in the system for conversion of a floor plan to a 3D scene for rendering of virtual reality, walk through videos and images, according to an embodiment. The method for conversion of a floor plan to a 3D scene for rendering of virtual reality, walk through videos and images comprising the step of,

[00047] at block 501, the user 201 can upload floor plan along with a customization setting 101 using the user interface device 202; the system for conversion of a floor plan to a 3D scene for rendering of virtual reality, walk through videos and images can obtain the floor plan along with a customization setting 101 from the user interface device 202;

[00048] at block 502, different symbols can be recognized using advanced computer vision and deep learning technologies for determining the walls, rooms, furniture used and its positions in the floor plan;

[00049] at block 503, the view and level merge for the exterior view of the house can be created by taking the plan views & the elevation view inside the floor plan; further,the height of the walls, position & dimensions of the windows and doors, slope of the roofs, roof styles can also be specified;further,the floor plan for a house can consist of several floors or levels that need to be merged into a single house. Each floor plan is iterated through the hyper-reality system and then finally merged together;

[00050] at block 504, the 3D scene can be generated by taking into account the customization settings and selected digital assets from the digital assets library; and

[00051] at block 505, the generated 3D scene can be rendered into VR scene or walkthrough videos or images 106. [00052] According to an embodiment,the present invention can allow homeowners or architects to visualize upcoming homes or visualizing furniture in context to their existing home by just using a floor plan. Users 201 can able to create 3D model of their homes by just uploading the floor plan which is then processed to identify the objects present in the floor plan. Then using the objects to create a 3D scene that can be rendered out as virtual reality video walkthrough or 2D images 106 stop in an automated manner. The benefit of this invention is that users 201 can be able to experience their homes as if they were physically present there in actual scale by using the benefit of virtual reality technologies as compared to the floor plan. Currently, creation of 3D scenes from floor plan is done manually whereas by being able to create it automatically by themselves gives the benefit of reduced cost, time & quality.

[00053] According to an exemplary embodiment, when the user 201 uploads the 2D floor plan to the system, the process engine 213 identifies the objects such as walls, floors, celling, doors, floor mat, fans, lights, chairs, sofas, bed and so on. Further, the engine calibrates the dimension of the floor plan and accordingly generates the 3D VR models for each object. After that, the 3D VR model is displayed in the VR display unit 206 to the user 201. If the user 201 wants to change any objects attributes or design then the engine provides an option to select the attributes or design or product itself from retail shop in online. Based on the change in object features, the customized VR visualization is generated.

[00054] According to an exemplary embodiment, the system can be utilized for applications that includes but is not limited to VR visualization for house, school, or any other building before construction, or after construction for interior decoration, VR visualization for scientific visualization, fashion designing, education, and so on.

[00055] The foregoing description of the specific embodiments will so fully reveal the general nature of the embodiments herein that others can, by applying current knowledge, readily modify and/or adapt for various applications such specific embodiments without departing from the generic concept, and, therefore, such adaptations and modifications should and are intended to be comprehended within the meaning and range of equivalents of the disclosed embodiments. It is to be understood that the phraseology or terminology employed herein is for the purpose of description and not of limitation. Therefore, while the embodiments herein have been described in terms of preferred embodiments, those skilled in the art will recognize that the embodiments herein can be practiced with modification within the spirit and scope of the embodiments as described herein.

Claims

I Claim:

1. A system for conversion of a floor plan to a 3D scene for rendering of virtual reality or walk through videos or images; wherein the system comprises of,

a user interface device (202) and a cloud platform (207);

wherein the cloud platform (207) includes an application server (208), an application interface (API ) (209), a work flow system (210), and digital assets and furniture Library (211);

characterized in that

the user interface device (202) includes a floor plan upload unit (203), a customization unit (204), a content downloader unit (205) and a virtual reality (VR), image and walkthrough viewer unit (206);

wherein the application server (208) includes a process engine (213); and wherein the process engine (213) configured to identify objects present in the floor plan and to generate 3D scenes based on the identified objects and to render 3D scene to video or virtual reality (VR) visualization by converting a floor plan into 3D scene in the interface device, for providing the VR visual or walk through videos or 2D renderings to a user (201).

2. The system of claim 1, wherein the floor plan upload unit (203) configured for uploading floor plans into the system; wherein the floor plan is a 2D floor plan or 3D floor plan or a vertical orthographic projection of a building and so on; and wherein the customization unit (204) configured for changing attributes of the objects present in the floor plan and also for adding new objects and/orspecific type of furniture from a database of available furniture into the 3D scene using the interface device.

3. The system of claim 1, wherein the content downloader unit (205) configured for allowing the user (201) to download the rendered VR or walkthrough videos or images (106) in a required format from the cloud platform (207) using the user interface device (202); and

wherein the virtual reality (VR), image and walkthrough viewer unit (206) configured for allowing the user (201) to view visualization of the floor plan as a home or interiors to provide the user (201) a virtual and augmented reality experience in the user interface device (202) using the rendered VR scene or walkthrough video or images (106).

4. The system of claim 1, wherein the process engine (213) further includes:

an image preprocessor module (301) configured for aiding object recognition by removing noise, isolating walls and furniture symbols, identifying region of interest, and handling colored and shaded floor plans using computer vision techniques;

a multi pass floor plan objects identifier module (302) configured for identifying symbols such as walls, rooms in the floor plan using a trained and an untrained machine learning techniques to generate 3D scenes; and

a view and level merge module (303) configured for creating an exterior view of the house by taking the floor plan views & an elevation view inside the floor plan.

5. The system of claim 1, wherein the process engine (213) further includes: a world scene builder module (304) configured for generate coordinate positions based on world coordinates for a 3D scene and creating type of 3D object based on objects identified in the multi pass floor plan objects identifier module (302); and a customization module (305) configured for recognizing different symbols from an input of customization settings in the application server (208).

The system of claim 1, wherein the process engine (213) further includes:

a 3D scene generator module (306) configured for creating actual 3D scene using

API (209) of external third-party modeling tools based on the inputs from the world space builder; and wherein the 3D models, textures, color of the walls, ceiling trims are obtained from the digital asset library based on the customization settings specified by the user (201);

a rendering module (307) configured for generating renders from the 3D scene by spawning render instances on the cloud platform (207); wherein the render output depends on an output option selected by the user (201); and

a package module (311) configured for compressing the renders to easier download. The system of claim 6, wherein the 3D scene generator module (306) further configured for creating 3D geometry for walls , flooring , roofs and so on, positioning of camera, lighting, external scenery, animation for walkthrough, interactivity; and

wherein the 3D scene generator module (306) further configured for assigning materials to the created geometry, importing pre-created 3D models and positioning pre-created 3D models based on the customization settings.

8. The system of claim 6, wherein output options for the rendering module (307) includes:

a VR scene generator module (310) configured for generating VR renders from the

3D scene by spawning render instances on the cloud platform (207);

avideo encoder module (309) configured for encoding video renders from the 3D scene by spawning render instances on the cloud platform (207); and

an image output module (308) configured for generating images from the 3D scene by spawning render instances on the cloud platform (207).

9. The system of claim 4, wherein the multi pass floor plan objects identifier module (302) comprises of sub modules to identify the objects in the floor plan; wherein the sub modules includes:

a scale & orientation calibration module (401) configured for handling scale and orientation for symbol detection; and

a deep learning module (403) configured forutilizing unsupervised deep learning for detecting the symbols.

10. The system of claim 4, wherein the multi pass floor plan objects identifier module (302) comprises of sub modules to identify the objects in the floor plan; wherein the sub modules includes:

a floor plan symbols linear Support Vector Machine (SVM) classifier module (402) configured for quickly identifying the symbols used in the floor plan using a trained linear SVM classifier based detection unit; wherein the training for each type of symbol is done on a training dataset that is then used for recognition.

11. The system of claim 9, wherein the sub modules further includes: a training updater module (404) configured for adding any unidentified symbol to the positive training database and adding incorrectly identified objects to the negative training dataset; wherein the training updater module (404) further configured for retaining the linear SVM classifier using an updated training dataset that includes the positive training database and negative training database;

a wall detection module (405) configured forcreating a structure of the house by identifying line segments on the floor plan; and

an object filter module (406) configured forremoving identified symbols from the floor plan to ease and increase accuracy of the objects recognition.

12. The system of claim 9, wherein the sub modules further includes:

a room identification module (407) configured for identifying rooms by taking connected walls into account;

a dimension detection module (408) configured foridentifying dimensions and set the length and width of the walls accordingly using text recognition; and

a decision module (409) configured forconforming recognized symbols by taking into account the inputs from the linear SVM classifier , deep learning classifier and the room context.

13. A method for providing virtual and augmented reality experience of a home or interiors to a user (201) comprising the step of,

obtaining a floor plan along with a customization setting (101) from a user interface device (202) to a system; recognizing different symbols using advanced computer vision and deep learning technologies for determining the walls, rooms, furniture used and its positions in the floor plan;

creating view and level merge for the exterior view of the house by taking the plan views & the elevation view inside the floor plan;

generating 3D scene by taking into account the customization settings and selected digital assets from the digital assets and furniture library (105); and

rendering generated 3D scene into VR scene or walkthrough videos or images

(106).