Method and system for automatically generating video according to 3D scene

Abstract

The invention discloses a method for automatically generating a video according to a 3D scene. The method comprises the following steps: 1) automatically generating a video of a 3D scene of a decoration space according to a style and a type selected by a user; 2) automatically calculating a video path in the 3D decoration scene, selecting one region as a starting region, entering other regions through a reasonable path, and then returning to the starting region; 3) automatically generating animations and characters corresponding to each style type in the 3D scene; and 4) automatically generating introduction copywriting according to the type and style of the 3D scene. The invention further discloses a system for automatically generating the video according to the 3D scene. The video production time is greatly shortened, the labor cost is reduced, and the efficiency is improved. Through optimization and intelligent planning, high video quality and vivid visual effect are ensured, and the video quality is improved. The decoration effect is visually and dynamically displayed, customers are helped to better understand the design scheme, the satisfaction degree is improved, and the experience feeling is enhanced.

Description

Technical Field

[0001] The invention belongs to the technical field of computer graphics processing and automatic video generation, and relates to a method and system for automatically generating videos according to 3D scenes. Background Art

[0002] In the current decoration design industry, after the effect is achieved, a picture is usually rendered and generated, which can be sent to customers or sent to WeChat Moments for promotion or directly to customers to show the design plan. There is no way to automatically generate a video. However, static pictures cannot fully show the sense of space and dynamic effects of decoration design. Videos require professionals to manually record materials and then manually produce them using video production software, which is very cumbersome and time-consuming, and ordinary people cannot do it at all. Moreover, every text change in the video requires the video to be modified again, and each frame needs to be produced, which takes a very long time and is very inefficient. Therefore, the market urgently needs a technology that can automatically convert 3D decoration scenes into dynamic videos to intuitively and efficiently display the decoration effects. Summary of the invention

[0003] An object of the present invention is to solve at least the above problems and / or disadvantages and to provide at least the advantages which will be described hereinafter.

[0004] Another object of the present invention is to provide a method and apparatus for automatically generating a video based on a 3D scene.

[0005] To this end, the technical solution provided by the present invention is: In a first aspect, a method for automatically generating a video according to a 3D scene includes: 1) Automatically generate a video of a 3D scene of a decorated space based on the style and type selected by the user; 2) Automatically calculate the video path in the 3D decoration scene, select one area as the starting area, enter each other area along a reasonable path, and then return to the starting area; 3) Automatically generate animation and text corresponding to each style type in the 3D scene; 4) Automatically generate introduction text according to the type and style of the 3D scene.

[0006] Preferably, in the method for automatically generating a video according to a 3D scene, step 2) specifically includes the following steps: Find all rooms connected to the starting area by doors; Starting from the starting area, walk from the door of one room to the door of another room along the shortest path; After entering each room, calculate and generate the path inside the room according to different rooms; After viewing all rooms, return to the starting area.

[0007] Preferably, in the method for automatically generating a video based on a 3D scene, in step 2), the living room is selected as the starting area.

[0008] Preferably, in the method of automatically generating a video according to a 3D scene, if there is a kitchen, the kitchen is given priority after walking through the living room; After entering the kitchen, the view moves along the kitchen cabinets and then returns to the kitchen door.

[0009] Preferably, in the method for automatically generating a video according to a 3D scene, the video generation path of the living room includes: Find the functional areas of the living room and generate them in the order of sofa, TV, dining table, wine cabinet, shoe cabinet, and balcony; If there is a sofa area, the visual angle moves from the left side to the right side facing the sofa. If there is no sofa area but a TV area, the visual angle moves from the left side to the right side of the TV area. If there is a sofa and a TV, move along the aisle between the sofa and the TV to the dining table; Then the vision moves from the dining table to the wine cabinet, from the wine cabinet to the shoe cabinet, and from the shoe cabinet to the balcony; If there is no area in the middle, it will automatically enter the next area.

[0010] Preferably, in the method for automatically generating a video based on a 3D scene, the paths of the video are all horizontal straight lines or vertical straight lines.

[0011] Preferably, in the method for automatically generating a video based on a 3D scene, after entering each area, a path in each area is calculated and generated based on different areas.

[0012] Preferably, in the method for automatically generating a video according to a 3D scene, the generation of a video of a bedroom includes: Find the functional areas of the bedroom: bed area, wardrobe area, window cabinet area; Starting from the bed area, the viewing angle automatically adjusts to face each area, and moves from left to right to look at each area. If there is no area in that area, it automatically goes to the next area.

[0013] Preferably, in the method for automatically generating a video based on a 3D scene, generating a video of a bathroom includes: entering the center point of the bathroom room, and rotating 360 degrees clockwise at the center point to look around the room.

[0014] Preferably, in the method for automatically generating a video according to a 3D scene, after viewing all the rooms, the user returns to the living room, cuts the viewing angle to the top of the sofa and TV, enters a bird's-eye view, rotates 360 degrees, and looks around the sofa and TV area.

[0015] Preferably, in the method for automatically generating a video based on a 3D scene, in step 3), the animation and text are always displayed in the video of the 3D decoration scene.

[0016] Preferably, in the method for automatically generating a video based on a 3D scene, in step 4), AI automatically generates an introduction copy based on the type and style of the decoration scene.

[0017] In the second aspect, a system for automatically generating a video according to a 3D scene includes: A generation module, which is used to automatically generate a video of a 3D scene of a decoration space according to the style and type selected by the user; A path calculation module is used to automatically calculate the video path in the 3D scene, select one area as the starting area, enter each other area with a reasonable path, and then return to the starting area; An animation and text generation module, which is used to automatically generate animation and text corresponding to each style type in the 3D scene; The copy generation module is used to automatically generate introduction copy according to the type and style of the 3D scene.

[0018] Optionally, the path calculation module is used to specifically implement the following steps: Find all rooms connected to the starting area by doors; Starting from the starting area, walk from the door of one room to the door of another room along the shortest path; After entering each room, calculate and generate the path inside the room according to different rooms; After viewing all rooms, return to the starting area.

[0019] Optionally, the living room is selected as the starting area.

[0020] Optionally, if there is a kitchen, go to the kitchen first after walking through the living room; After entering the kitchen, the view moves along the kitchen cabinets and then returns to the kitchen door.

[0021] Optionally, the video generation path of the living room includes: Find the functional areas of the living room and generate them in the order of sofa, TV, dining table, wine cabinet, shoe cabinet, and balcony; If there is a sofa area, the visual angle moves from the left side to the right side facing the sofa. If there is no sofa area but a TV area, the visual angle moves from the left side to the right side of the TV area. If there is a sofa and a TV, move along the aisle between the sofa and the TV to the dining table; Then the vision moves from the dining table to the wine cabinet, from the wine cabinet to the shoe cabinet, and from the shoe cabinet to the balcony; If there is no area in the middle, it will automatically enter the next area. Optionally, the paths of the videos are all horizontal straight lines or vertical straight lines.

[0022] Optionally, after entering each area, the path in each area is calculated and generated according to different areas.

[0023] Optionally, for bedroom video generation, include: Find the functional areas of the bedroom: bed area, wardrobe area, window cabinet area; Starting from the bed area, the viewing angle automatically adjusts to face each area, and moves from left to right to look at each area. If there is no area in that area, it automatically goes to the next area.

[0024] Optionally, the video generation of the bathroom includes: entering the center point of the bathroom room, and rotating 360 degrees clockwise at the center point to look around the room.

[0025] Optionally, after viewing all the rooms, return to the living room, cut the view to the top of the sofa and TV, enter the bird's-eye view, rotate 360 ​​degrees, and look around the sofa and TV area.

[0026] Optionally, the animation and text are always displayed in the video of the 3D decoration scene.

[0027] Optionally, AI automatically generates introductory copy based on the type and style of the decoration scene.

[0028] The present invention has at least the following beneficial effects: The present invention can solve the problem that designers and shop assistants cannot easily and automatically generate videos according to the type and style of 3D scenes selected by users; and can solve the problem that the text on the same video needs to be remade. The present invention can automatically generate the content of the text, and also avoids the problem that the shop assistants or designers need to write introduction texts to introduce the decoration design texts of different styles in different rooms in the design, saving production time. In addition, when the method of the present invention is used to generate a video for the whole house plan, there is no need to manually calculate the walking path according to the house type. The present invention can automatically calculate the viewing path to ensure that the video can view every room.

[0029] The automated process of the present invention greatly shortens the video production time, reduces labor costs, and improves efficiency. The present invention improves the video quality by ensuring high video quality and realistic visual effects through optimization and intelligent planning. The present invention dynamically displays the decoration effect, helps customers better understand the design plan, improves satisfaction, and enhances the experience.

[0030] Other advantages, objectives and features of the present invention will be embodied in part through the following description, and in part will be understood by those skilled in the art through study and practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 This is a display picture of a template entered into the system background by the present invention, in which the owner information and the decoration company information are displayed in the upper left corner and the lower right corner.

[0032] Figure 2 The real owner and decoration company information entered by the user after selecting the template when using the system in the present invention is displayed.

[0033] Figure 3 This is a screenshot of the video effect generated by the system of the present invention based on the template and the real information entered during use.

[0034] Figure 4 This is a display picture of another template entered into the system background of the present invention, in which the owner information and the decoration company information are displayed in the upper left corner and the lower right corner.

[0035] Figure 5 When the user of the present invention uses the system, he / she selects the template and enters the real owner and decoration company information.

[0036] Figure 6 This is a screenshot of the video effect generated by the system of the present invention based on the template and the real information entered during use.

[0037] Figure 7 When the system of the present invention generates a video, it uses AI to automatically generate text introducing the room based on the current room type "living room" and the current living room style "wabi-sabi".

[0038] Figure 8 When the system of the present invention generates a video, it uses AI to automatically generate text introducing the room based on the current room type "kitchen" and the current kitchen style "wabi-sabi".

[0039] Fig. 9 When the system of the present invention generates a video, it uses AI to automatically generate text introducing the room based on the current room type "bathroom" and the current bathroom style "Japanese style". DETAILED DESCRIPTION

[0040] The present invention is further described in detail below in conjunction with the accompanying drawings so that those skilled in the art can implement the invention with reference to the description.

[0041] It should be understood that terms such as “having”, “including” and “comprising” used herein do not specify the existence or addition of one or more other elements or combinations thereof.

[0042] like Figures 1 to 9As shown, the present invention provides a method for automatically generating a video according to a 3D scene, comprising: 1) Automatically generate a video of a 3D scene of a decorated space based on the style and type selected by the user, including room structure, furniture layout, material mapping, etc. Analyze the input 3D scene, identify and optimize the geometric model, lighting effects, material properties, etc. in the scene, and ensure the authenticity and rendering efficiency of the scene.

[0043] 2) Automatically calculate the video path in the 3D decoration scene, select one area as the starting area, enter each other area with a reasonable path, and then return to the starting area; based on the scene content, automatically plan a camera path to simulate the natural movement of people in the room and show the decoration effect from multiple angles. Path planning takes into account the smoothness of perspective switching and the comprehensiveness of information coverage.

[0044] 3) Automatically generate animation and text corresponding to each style type in the 3D scene; Figure 3 and Figure 6 It can be seen that the template determines the effect in the video, and the input when used determines the content of the text in the video.

[0045] 4) Automatically generate introduction text according to the type and style of the 3D scene.

[0046] The present invention can solve the problem that designers and shop assistants cannot easily and automatically generate videos according to the type and style of 3D scenes selected by users; and can solve the problem that the text on the same video needs to be remade. The present invention can automatically generate the content of the text, and also avoids the problem that the shop assistants or designers need to write introduction texts to introduce the decoration design texts of different styles in different rooms in the design, saving production time. In addition, when the method of the present invention is used to generate a video for the whole house plan, there is no need to manually calculate the walking path according to the house type. The present invention can automatically calculate the viewing path to ensure that the video can view every room.

[0047] The automated process of the present invention greatly shortens the video production time, reduces labor costs, and improves efficiency. The present invention improves the video quality by ensuring high video quality and realistic visual effects through optimization and intelligent planning. The present invention dynamically displays the decoration effect, helps customers better understand the design plan, improves satisfaction, and enhances the experience.

[0048] In one embodiment of the present invention, preferably, step 2) specifically includes the following steps: Find all rooms connected to the starting area by doors; Starting from the starting area, walk from the door of one room to the door of another room along the shortest path; After entering each room, calculate and generate the path inside the room according to different rooms; After viewing all rooms, return to the starting area.

[0049] The route planned in this way is reasonable and easy to realize intelligence.

[0050] In one embodiment of the present invention, preferably, in step 2), the living room is selected as the starting area. Generally, the living room is located in the central area, which saves the path.

[0051] In one embodiment of the present invention, preferably, if there is a kitchen and living room, go to the kitchen first after walking through it; After entering the kitchen, the view moves along the kitchen cabinets and then returns to the kitchen door.

[0052] In one embodiment of the present invention, preferably, the video generation path of the living room includes: Find the functional areas of the living room and generate them in the order of sofa, TV, dining table, wine cabinet, shoe cabinet, and balcony; If there is a sofa area, the visual angle moves from the left side to the right side facing the sofa. If there is no sofa area but a TV area, the visual angle moves from the left side to the right side of the TV area. If there is a sofa and a TV, move along the aisle between the sofa and the TV to the dining table; Then the vision moves from the dining table to the wine cabinet, from the wine cabinet to the shoe cabinet, and from the shoe cabinet to the balcony; If there is no area in the middle, it will automatically enter the next area. In one embodiment of the present invention, preferably, the paths of the videos are all horizontal straight lines or vertical straight lines.

[0053] In one of the embodiments of the present invention, preferably, after entering each area, a path in each area is calculated and generated according to different areas.

[0054] In one embodiment of the present invention, preferably, the video generation of the bedroom includes: Find the functional areas of the bedroom: bed area, wardrobe area, window cabinet area; Starting from the bed area, the viewing angle automatically adjusts to face each area, and moves from left to right to look at each area. If there is no area in that area, it automatically goes to the next area.

[0055] In one of the embodiments of the present invention, preferably, the generation of the video of the bathroom includes: entering the center point of the bathroom room, rotating 360 degrees clockwise at the center point to look around the room.

[0056] In one embodiment of the present invention, as a preference, after viewing all the rooms, the user returns to the living room, switches the viewing angle to the top of the sofa and TV, enters a bird's-eye view, rotates 360 degrees, and looks around the sofa and TV area.

[0057] In one of the embodiments of the present invention, preferably, in step 3), the animation and text are always displayed in the video of the 3D decoration scene.

[0058] In one embodiment of the present invention, preferably, in step 4), AI automatically generates an introduction copy based on the type and style of the decoration scene.

[0059] The present invention also provides a system for automatically generating a video according to a 3D scene, comprising: A generation module, which is used to automatically generate a video of a 3D scene of a decoration space according to the style and type selected by the user; A path calculation module is used to automatically calculate the video path in the 3D scene, select one area as the starting area, enter each other area with a reasonable path, and then return to the starting area; An animation and text generation module, which is used to automatically generate animation and text corresponding to each style type in the 3D scene; The copy generation module is used to automatically generate introduction copy according to the type and style of the 3D scene.

[0060] Furthermore, the path calculation module is used to specifically implement the following steps: Find all rooms connected to the starting area by doors; Starting from the starting area, walk from the door of one room to the door of another room along the shortest path; After entering each room, calculate and generate the path inside the room according to different rooms; After viewing all rooms, return to the starting area.

[0061] Furthermore, the living room is selected as the starting area.

[0062] Furthermore, if there is a kitchen, go to the kitchen first after walking through the living room; After entering the kitchen, the view moves along the kitchen cabinets and then returns to the kitchen door.

[0063] Furthermore, the video generation path of the living room includes: Find the functional areas of the living room and generate them in the order of sofa, TV, dining table, wine cabinet, shoe cabinet, and balcony; If there is a sofa area, the visual angle moves from the left side to the right side facing the sofa. If there is no sofa area but a TV area, the visual angle moves from the left side to the right side of the TV area. If there is a sofa and a TV, move along the aisle between the sofa and the TV to the dining table; Then the vision moves from the dining table to the wine cabinet, from the wine cabinet to the shoe cabinet, and from the shoe cabinet to the balcony; If there is no area in the middle, it will automatically enter the next area; Furthermore, the paths of the videos are all horizontal straight lines or vertical straight lines.

[0064] Furthermore, after entering each area, the path in each area is calculated and generated according to different areas.

[0065] Furthermore, the video generation of the bedroom includes: Find the functional areas of the bedroom: bed area, wardrobe area, window cabinet area; Starting from the bed area, the viewing angle automatically adjusts to face each area, and moves from left to right to look at each area. If there is no area in that area, it automatically goes to the next area.

[0066] Furthermore, the generation of the bathroom video includes: entering the center point of the bathroom room, and rotating 360 degrees clockwise at the center point to look around the room.

[0067] Furthermore, after viewing all the rooms, return to the living room, cut the perspective to the top of the sofa and TV, enter the bird's-eye view, rotate 360 ​​degrees, and look around the sofa and TV area.

[0068] Furthermore, the animation and text are always displayed in the video of the 3D decoration scene.

[0069] Furthermore, AI automatically generates introductory copy based on the type and style of the decoration scene.

[0070] In order to enable those skilled in the art to better understand the technical solution of the present invention, the following embodiments are provided for further explanation: like Figures 1 to 9 As shown, the present invention provides a method for automatically generating a video according to a 3D scene, comprising: 1) Automatically generate videos of various resolutions based on 3D scenes; 2) Automatically calculate the video path based on the 3D scene, starting from the living room, entering each room along a reasonable path, and then returning to the living room; 3) Automatically generate corresponding animations and texts based on the background template; 4) AI automatically generates introduction copy based on room type and room style.

[0071] 1. Calculate the path from the living room: Find all rooms connected to the living room by doors If there is a kitchen, go to the kitchen first after walking through the living room. Bedrooms, bathrooms and other types of rooms have the same priority Starting from the living room, follow the shortest path from the door of one room to the door of another room All paths are straight lines, and they are horizontal and vertical, and no diagonal lines are allowed. After entering each room, calculate and generate the path in the room according to different rooms living room: 1) Find the functional areas of the living room, in order: sofa, TV, dining table, wine cabinet, shoe cabinet, balcony; 2) If there is a sofa area, the view will move from the left to the right facing the sofa. If there is no sofa area but a TV area, move from the left to the right of the TV area. 3) If there is a sofa and a TV, move along the aisle between the sofa and the TV to the dining table; 4) Move from the dining table to the wine cabinet, from the wine cabinet to the shoe cabinet, and from the shoe cabinet to the balcony; 5) If there is no area in the middle, it will automatically enter the next area.

[0072] Kitchen: After entering the kitchen, the view moves along the kitchen cabinets and then returns to the kitchen door. bedroom: 1) Find the functional areas of the bedroom: bed area, wardrobe area, window cabinet area 2) Starting from the bed area, the viewing angle automatically adjusts to face each area, panning from left to right to view each area. If the area does not appear, it automatically moves to the next area. Bathroom: Enter the center of the bathroom room and rotate 360 ​​degrees clockwise from the center point to look around the room. After viewing all the rooms, return to the living room, cut the perspective to the top of the sofa and TV, enter the bird's-eye view, rotate 360 ​​degrees, and look around the sofa and TV area.

[0073] 2. Create corresponding templates according to different purposes. When generating a video, select the corresponding template to automatically add the corresponding text and animation effects to the video.

[0074] 3. When generating a video, an introduction text is automatically generated based on the type and style of the room.

[0075] The number of modules and processing scales described here are used to simplify the description of the present invention. Applications, modifications and variations of the present invention are obvious to those skilled in the art.

[0076] Although the embodiments of the present invention have been disclosed as above, they are not limited to the applications listed in the specification and the implementation modes, and they can be fully applied to various fields suitable for the present invention. For those familiar with the art, additional modifications can be easily implemented. Therefore, without departing from the general concept defined by the claims and the scope of equivalents, the present invention is not limited to the specific details and the illustrations shown and described herein.

Claims

1. A method for automatically generating a video based on a 3D scene, characterized in that: include: 1) Automatically generate a video of a 3D scene of a decorated space based on the style and type selected by the user; 2) Automatically calculate the video path in the 3D decoration scene, select one area as the starting area, enter each other area along a reasonable path, and then return to the starting area; 3) Automatically generate animation and text corresponding to each style type in the 3D scene; 4) Automatically generate introduction text according to the type and style of the 3D scene.

2. The method for automatically generating a video according to a 3D scene according to claim 1, characterized in that: Step 2) specifically includes the following steps: Find all rooms connected to the starting area by doors; Starting from the starting area, walk from the door of one room to the door of another room along the shortest path; After entering each room, calculate and generate the path inside the room according to different rooms; After viewing all rooms, return to the starting area.

3. The method for automatically generating a video according to a 3D scene according to claim 1, characterized in that: In step 2), the living room is selected as the starting area.

4. The method for automatically generating a video according to a 3D scene according to claim 3, characterized in that: If there is a kitchen, go to the kitchen first after walking through the living room; After entering the kitchen, the view moves along the kitchen cabinets and then returns to the kitchen door.

5. The method for automatically generating a video according to a 3D scene according to claim 3, characterized in that: The video generation path for the living room includes: Find the functional areas of the living room and generate them in the order of sofa, TV, dining table, wine cabinet, shoe cabinet, and balcony; If there is a sofa area, the visual angle moves from the left side to the right side facing the sofa. If there is no sofa area but a TV area, the visual angle moves from the left side to the right side of the TV area. If there is a sofa and a TV, move along the aisle between the sofa and the TV to the dining table; Then the vision moves from the dining table to the wine cabinet, from the wine cabinet to the shoe cabinet, and from the shoe cabinet to the balcony; If there is no area in the middle, it will automatically enter the next area.

6. The method for automatically generating a video according to a 3D scene according to claim 1, characterized in that: The paths of the videos are all horizontal straight lines or vertical straight lines.

7. The method for automatically generating a video according to a 3D scene according to claim 1, characterized in that: After entering each area, the path inside each area is calculated and generated according to the different areas.

8. The method for automatically generating a video according to a 3D scene as claimed in claim 3, characterized in that: For bedroom video generation, this includes: Find the functional areas of the bedroom: bed area, wardrobe area, window cabinet area; Starting from the bed area, the viewing angle automatically adjusts to face each area, and moves from left to right to look at each area. If there is no area in that area, it automatically goes to the next area.

9. The method for automatically generating a video according to a 3D scene according to claim 1, characterized in that: The video generation of the bathroom includes: entering the center point of the bathroom room, rotating 360 degrees clockwise at the center point to look around the room; After viewing all the rooms, return to the living room, switch the view to the top of the sofa and TV, enter the bird's-eye view, rotate 360 ​​degrees, and look around the sofa and TV area; In step 3), the animation and text are always displayed in the video of the 3D decoration scene; In step 4), AI automatically generates introduction copy based on the type and style of the decoration scene.

10. A system for automatically generating a video based on a 3D scene, characterized in that: include: A generation module, which is used to automatically generate a video of a 3D scene of a decoration space according to the style and type selected by the user; A path calculation module is used to automatically calculate the video path in the 3D scene, select one area as the starting area, enter each other area with a reasonable path, and then return to the starting area; An animation and text generation module, which is used to automatically generate animation and text corresponding to each style type in the 3D scene; The copy generation module is used to automatically generate introduction copy according to the type and style of the 3D scene.

Images