A video generation method and device, computer equipment and a storage medium

Abstract

The present disclosure provides a video generation method and device, computer equipment and a storage medium, wherein the method comprises: recording a performance behavior of a target object during a performance process of the target object to obtain recorded performance data; recording a director operation event occurring in the performance process to obtain event track data in response to the director operation event; the event track data records event information and an event occurrence time of each director operation event; and editing the recorded performance data based on the event track data to generate a target video.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of Internet, in particular, to a video generation method and device, computer equipment and storage medium. BACKGROUND

[0002] At present, after a video is shot, the props, lights, and performance behaviors of actors in the video cannot be modified. When a certain shot (for example, the performance behavior of an actor or the placement position of a prop) in the video needs to be adjusted, the adjusted shot needs to be re-shot to obtain an adjusted video, thereby wasting a lot of human and material resources. SUMMARY

[0003] The present disclosure provides at least a video generation method, device, computer equipment, and storage medium.

[0004] In a first aspect, the present disclosure provides a video generation method, which includes: recording performance behaviors of at least one target object during a performance process of the target object to obtain recorded performance data; recording director operation events occurring in the performance process to obtain event track data; the event track data records event information and event occurrence time of each of the director operation events; and editing the recorded performance data based on the event track data to generate a target video.

[0005] In an optional implementation, before recording the performance behaviors of the target object, the method further includes: recording each scene element associated with the performance process to obtain recorded scene element data; and the director operation events occurring in the performance process include performing a first director operation on a scene element in the performance process of the target object based on the scene element data.

[0006] In an optional implementation, the scene element includes a scene prop; and the first director operation on the scene element in the performance process of the target object is performed based on pre-recorded scene prop data by performing at least one of the following operations on the scene prop in the performance process of the at least one target object: adding, deleting, or adjusting a pose.

[0007] In an optional implementation, the scene element includes a light; and the first director operation on the scene element in the performance process of the target object is performed based on pre-recorded various light data by performing a switching operation on the light in the performance process of the at least one target object.

[0008] In an optional implementation, the scene element includes a scene special effect; and the first director operation on the scene element in the performance process of the target object is performed according to the following steps: adding a target scene special effect in the performance process of the target object based on various pre-recorded special effect data.

[0009] In an optional implementation, the scene element includes a virtual lens; and the first director operation on the scene element in the performance process of the target object is performed according to the following steps: switching the shooting angle of the virtual lens according to the current pose of the target object or a pre-set plot in the performance process of the at least one target object.

[0010] In an optional implementation, the at least one target object includes a target virtual role; and before the performance behavior of the target object is recorded, the method further includes: generating model data of the target virtual role; and the director operation event occurring in the performance process includes: performing a second director operation on the target virtual role in the performance process of the at least one target object based on the model data of the target virtual role; and the second director operation includes: role entry and / or role exit.

[0011] In an optional implementation, the editing of the post-recording performance data based on the event track data to generate a target video includes: performing at least one of event addition, event deletion, and event sequence adjustment of the director operation event on the post-recording performance data based on the event track data.

[0012] In an optional implementation, the editing of the post-recording performance data to generate a target video includes: editing the post-recording performance data to generate an initial video; and performing clipping processing on the obtained initial video to obtain the target video.

[0013] In a second aspect, the embodiments of the present disclosure further provide a video generation apparatus, including: a recording unit configured to record performance behavior of at least one target object in a performance process of the target object to obtain post-recording performance data; a responding unit configured to record a director operation event occurring in the performance process in response to the director operation event to obtain event track data; the event track data records event information and event occurrence time of each director operation event; and an editing unit configured to edit the post-recording performance data based on the event track data to generate a target video.

[0014] In a third aspect, the embodiments of the present disclosure further provide a computer device, comprising a processor, a memory and a bus, the memory stores machine readable instructions executable by the processor, when the computer device is running, the processor and the memory communicate through the bus, and the machine readable instructions are executed by the processor to perform the steps of the first aspect or any possible implementation manner of the first aspect.

[0015] In a fourth aspect, the embodiments of the present disclosure further provide a computer readable storage medium, the computer readable storage medium stores a computer program, when the computer program is run by a processor, the steps of the first aspect or any possible implementation manner of the first aspect are performed.

[0016] As described above, the director operation events occurring in the performance process can be recorded to obtain event track data, so that the director operation events in the performance process are independent of each other. Then, the recorded performance data can be edited based on the event track data, that is, any event information and event occurrence time in the performance process can be edited to realize the editing of the recorded performance data, thereby improving the flexibility and diversity of editing the recorded performance data.

[0017] In order to make the above objectives, characteristics and advantages of the present disclosure more apparent, the following will describe a preferred embodiment in detail, and the accompanying drawings will be described as follows. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following will briefly introduce the drawings needed to be used in the embodiments, the drawings herein are incorporated into the description and form a part of the description, the drawings show the embodiments consistent with the present disclosure, and are used to illustrate the technical solutions of the present disclosure together with the description. It should be understood that the following drawings only show some embodiments of the present disclosure, and therefore should not be regarded as a limitation on the scope, and for those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0019] Figure 1 A flow chart of a video generation method provided by the embodiments of the present disclosure is shown;

[0020] Figure 2 A flow chart of a method for editing recorded performance data to generate a target video provided by the embodiments of the present disclosure is shown;

[0021] Figure 3 A flow chart of a video generation method provided by the embodiments of the present disclosure is shown;

[0022] Figure 4 FIG. 1 shows a schematic diagram of a video generation apparatus according to an embodiment of the present disclosure;

[0023] Figure 5 FIG. 2 shows a schematic diagram of a computer device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0024] In order to make the objects, technical solutions and advantages of the embodiments of the present disclosure clearer, the following will be combined with the accompanying drawings for the embodiments of the present disclosure to clearly and completely describe the technical solutions of the embodiments of the present disclosure. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, but not all the embodiments. The components of the embodiments of the present disclosure described and shown in the accompanying drawings can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present disclosure provided in the accompanying drawings is not intended to limit the scope of the claimed present disclosure, but only represents selected embodiments of the present disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present disclosure.

[0025] It should be noted that: similar reference numerals and letters represent similar items in the following drawings, therefore, once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings.

[0026] The term "and / or" herein is only used to describe an associated relationship, which means that there can be three relationships, for example, A and / or B can mean that A exists alone, A and B exist together, and B exists alone. In addition, the term "at least one" herein means any one of a plurality or any combination of at least two of a plurality, for example, including at least one of A, B and C can mean including any one or more elements selected from the set consisting of A, B and C.

[0027] It is found through research that at present, after a video is shot, the props, lighting, and performance behavior of actors in the video cannot be modified. When a certain shot (for example, the performance behavior of an actor, or the placement position of a prop, etc.) in the video needs to be adjusted, the adjusted shot has to be re-shot to obtain an adjusted video, thereby wasting a lot of human and material resources.

[0028] Based on the above research, the present disclosure provides a video generation method, device, computer equipment and storage medium. As can be known from the above description, the director operation event occurring in the performance process can be recorded to obtain event track data, so that the director operation events in the performance process are independent of each other. Then, the recorded performance data can be edited based on the event track data, that is, any event information and event occurrence time in the performance process can be edited to edit the recorded performance data, thereby improving the flexibility and diversity of editing the recorded performance data.

[0029] To facilitate the understanding of the present embodiment, first, a video generation method disclosed by the present embodiment is introduced in detail, wherein the video generation method disclosed by the present embodiment can be applied to a video live software or a video director software. At this time, the video live software or the video director software can be set in a computer device with certain computing power. The computer device can be understood as a terminal device, for example, the computer device can be a mobile phone, a tablet, a computer, etc.

[0030] Referring to FIG. 1, Figure 1 The method comprises steps S101-S105, wherein:

[0031] S101: In the performance process of at least one target object, the performance behavior of the target object is recorded to obtain recorded performance data.

[0032] Here, the target object can be a real person, at this time, the target object can be an XX actor, or an XX anchor, etc. Alternatively, the target object can also be a virtual role, at this time, the virtual role can be a virtual image corresponding to a real person, or a self-defined virtual image, or an AI (Artificial Intelligence) virtual image, which is not limited by the present disclosure.

[0033] In the present embodiment, the performance process of at least one target object indicates the process from the beginning of the performance behavior of at least one target object to the end of the performance behavior.

[0034] In the embodiments of the present disclosure, the recording of the performance behavior of the target object can include recording at least one of the following data: voice, expression, action. That is, after recording the performance behavior of the target object, the obtained post-recording performance data can correspond to at least one of the following: voice data, expression data, and action data. At this time, each of the above-mentioned post-recording performance data obtained can correspond to one track data. For example, the voice data can correspond to voice track data, the expression data can correspond to expression track data, and the action data can correspond to action track data.

[0035] In the embodiments of the present disclosure, the recording of the performance behavior of the target object can be realized by starting the video recording function in the video director software (or video live broadcast software), and obtaining post-recording performance data.

[0036] S103: In response to the director operation event occurring in the performance process, recording the director operation event to obtain event track data; the event track data records event information and event occurrence time of each director operation event.

[0037] In the embodiments of the present disclosure, the director operation event is used to indicate an event of adjusting the target object, the performance behavior of the target object, the scene element, etc. in the performance process, for example, the director operation event can be at least one of the following: adjusting the number of target objects (for example, adding target objects, deleting target objects, changing target objects), adjusting the performance behavior of the target object (for example, adding the performance behavior of the target object, deleting the performance behavior of the target object, changing the performance behavior of the target object), adding or deleting scene props, switching indoor lights, adjusting the recording angle in the performance process, etc.

[0038] In the embodiments of the present disclosure, the event information of the director operation event can be understood as the specific event content corresponding to the director operation event, for example, in the case that the director operation event is "adding a target object" and the added target object is "target object 1", the event information of the director operation event can be "adding target object 1". For another example, in the case that the director operation event is "adding a performance behavior of a target object" and the added performance behavior of the target object is "performance behavior A", the event information of the director operation event can be "adding performance behavior A of target object 1".

[0039] In the embodiments of the present disclosure, the event occurrence time of the director operation event can only include the start time of the director operation event, or can include the start time and the end time of the director operation event.

[0040] For example, if the director's operation event is "Add Target Object," and the newly added target object is "Target Object 1," the event occurrence time of this director's operation event can be the time when adding Target Object 1 begins during the performance. Alternatively, the event occurrence time of this director's operation event can also be the time when adding Target Object 1 begins during the performance and the time when Target Object 1 is deleted during the performance. Where the performance behavior of Target Object 1 continues until the end of recording, the time when Target Object 1 is deleted during the performance is the time when recording ends.

[0041] S105: Based on the event track data, edit the recorded performance data to generate the target video.

[0042] As described above, the system can respond to director operation events occurring during the performance, recording these events to obtain event track data. This ensures that each director operation event during the performance is independent of the others. Subsequently, the recorded performance data can be edited based on this event track data. Specifically, any event information and its occurrence time during the performance can be edited, thereby improving the flexibility and versatility of post-recorded performance data editing.

[0043] In an optional implementation, before recording the performance behavior of the target object, the embodiments of this disclosure may also record each scene element associated with the performance process separately to obtain the recorded scene element data.

[0044] Here, the aforementioned scene elements can be understood as elements in the scene where the target object's performance takes place. For example, the scene element can be at least one of the following: scene props, scene effects, lighting, and virtual camera.

[0045] In this embodiment of the disclosure, before recording the performance behavior of the target object, the various scene elements required during the performance process (i.e., the various scene elements associated with the performance process) can be determined first. Then, the video recording button in the video directing software (or video live streaming software) can be used to record each scene element to obtain the recorded data of each scene element.

[0046] Based on this, in response to the director operation events that occur during the performance, this embodiment of the disclosure can perform a first director operation on the scene elements during the performance of the target object based on the scene element data.

[0047] Here, the first director operation can include at least one of element addition, element deletion, and element adjustment of the scene element. The element adjustment can be understood as adjusting any one of the following of the scene element: size of the scene element, direction of the scene element, type of the scene element, and the like.

[0048] For example, scene prop B can be replaced by scene prop C. At this time, scene prop B in the performance process of the target object can be deleted, and scene prop C can be added. For another example, when the scene element is light, the light in the performance process of the target object can be adjusted. For example, the color of the light can be changed from red to yellow. At this time, the red light in the performance process of the target object can be adjusted to yellow light.

[0049] In the embodiments of the present disclosure, when the types of the scene elements are different, the first director operation performed on the scene elements is also different. The following will be introduced in detail in different cases.

[0050] Case one: the scene element includes a scene prop. At this time, the first director operation performed on the scene element in the performance process of the target object can be performed in the following manner:

[0051] At least one of the following operations is performed on the scene prop in the performance process of the at least one target object based on the pre-recorded scene prop data: adding, deleting, and pose adjustment.

[0052] In the embodiments of the present disclosure, a plurality of pre-set scene props can be recorded before the performance behavior of the target object is recorded, to obtain pre-recorded scene prop data. The pre-set scene prop can be an object required in the performance process, for example, the scene prop can be home furnishings (for example, a sofa, a suitcase), or can be a decoration (for example, a mural, a vase), and the like.

[0053] In the embodiments of the present disclosure, when the adding operation is performed on the scene prop, a data list in which the pre-recorded scene prop data is located can be displayed. Then, the scene prop data in the data list can be selected, and the scene prop corresponding to the selected scene prop data can be added to the performance process.

[0054] In the embodiments of the present disclosure, after the scene prop in the performance process is triggered, the scene prop can be deleted from the performance process in response to the deletion operation of the scene prop.

[0055] In the embodiments of the present disclosure, in the case of performing the pose adjustment operation on the scene prop, in a possible implementation, the pose adjustment range can be displayed after triggering the scene prop. Then, the pose adjustment of the scene prop can be implemented in response to the triggering operation on the pose adjustment range.

[0056] Case two: the scene element includes light. At this time, the first director operation on the scene element in the performance process of the target object can be performed in the following manner:

[0057] Switching operation is performed on the in-scene light in the performance process of the at least one target object based on various pre-recorded light data.

[0058] In the embodiments of the present disclosure, the light data can indicate at least one of the following: light color, light size, light flickering mode, light flickering frequency, light quantity, light sorting mode, and the like.

[0059] Each light data can include at least one light sub-data. For example, in the case where the light data indicates the light color, the light sub-data included in the light data can be yellow, red, green, and the like, which are not listed one by one here. For another example, in the case where the light data indicates the light size, the light sub-data included in the light data can be large light, small light, and the like.

[0060] In the embodiments of the present disclosure, in the case of performing the switching operation on the in-scene light in the performance process of the at least one target object, the light data indicated by the switching operation can be determined first, and the target light sub-data can be determined from the at least one light sub-data included in the indicated light data. Then, the in-scene light in the performance process can be switched to the light corresponding to the target light sub-data.

[0061] Case three: the scene element includes scene special effects. At this time, the first director operation on the scene element in the performance process of the target object can be performed in the following manner:

[0062] The target scene special effect is added in the performance process of the target object based on various pre-recorded special effect data.

[0063] In the embodiments of the present disclosure, the scene special effect can include sound special effect and visual special effect. Based on this, the pre-recorded various special effect data can include sound special effect data and visual special effect data.

[0064] The sound effect data can include object sound effect data and background sound effect data. The object sound effect data is sound effect data of a target object in a performance process. For example, the object sound effect data can be "doll sound effect" or "Cantonese sound effect".

[0065] In the embodiments of the present disclosure, the visual effect data can indicate an effect of changing the display effect of the target object in the performance process. For example, the visual effect can be a sticker effect, an explosion effect, or an animation effect.

[0066] In the embodiments of the present disclosure, the target scene effect can be determined in response to a selection operation of the pre-recorded effect data in the performance process of the target object, and the target scene effect can be added to the target object.

[0067] Case four: the scene element includes a virtual lens. At this time, the first director operation can be performed on the scene element in the performance process of the target object in the following manner:

[0068] In the performance process of the at least one target object, the shooting angle of the virtual lens is switched according to the current pose of the target object or a pre-set plot.

[0069] In the embodiments of the present disclosure, the current pose of the target object can indicate a direction in which the target object faces.

[0070] In the embodiments of the present disclosure, a correspondence between the virtual camera and the current pose of the target object can be pre-set. Then, the shooting angle of the virtual lens matched with the current pose of the target object can be determined based on the pre-set correspondence. When the shooting angle of the virtual lens does not match the current pose of the target object, the shooting angle of the virtual lens can be switched to the shooting angle matched with the current pose of the target object.

[0071] For example, the correspondence between the virtual camera and the current pose of the target object can be pre-set as that the virtual camera shoots the front face of the target object. At this time, the shooting angle of the virtual camera in the direction indicated by the current pose of the target object can be determined as the shooting angle of the virtual lens matched with the current pose of the target object. When the shooting angle of the virtual lens does not match the current pose of the target object, the shooting angle of the virtual lens can be switched to the shooting angle matched with the current pose of the target object.

[0072] In the embodiments of the present disclosure, the pre-set plot can be understood as a shooting effect of a performance process of the target object. For example, the pre-set plot can be a shooting of a performance behavior of the target object in a back view state, or can be a shooting of a performance behavior of the target object in a front view state, or can be a shooting of a performance behavior of the target object in a side view state, and the like.

[0073] In this case, the shooting angle of the virtual camera can be determined based on the pre-set plot. For example, in the case where the pre-set plot is a shooting of a performance behavior of the target object in a front view state, the shooting angle of the virtual camera corresponding to the direction indicated by the front view of the target object can be determined as a shooting angle matched with the pre-set plot. When the shooting angle of the virtual camera does not match the pre-set plot, the shooting angle of the virtual camera can be switched to a shooting angle matched with the pre-set plot.

[0074] In the above embodiments, each scene element associated with the performance process can be recorded before the performance behavior of the target object is recorded, and each recorded scene element data is obtained, so that the reuse of each scene element can be realized, and the scene arrangement cost is reduced. Then, the first director operation can be performed on the scene element in the performance process of the target object, so that the flexible and changeable scene element in the performance process can be realized through the first director operation, and the recording cost in the performance process is reduced, and the resources are saved.

[0075] In an optional embodiment, before the performance behavior of the target object is recorded, the model data of the target virtual role can be generated in the case where the at least one target object includes the target virtual role.

[0076] In the embodiments of the present disclosure, the target virtual role can be a virtual image corresponding to a real person, or can be a self-defined virtual image. The model data of the target virtual role can be used to indicate the display effect of the target virtual role.

[0077] In the embodiments of the present disclosure, the image corresponding to the target virtual role can be determined first, and then the image is modeled to obtain a three-dimensional model corresponding to the target virtual role. At this time, the data corresponding to the three-dimensional model can be the model data of the target virtual role.

[0078] In addition, the model data of the target virtual role can further include limb motion data and / or facial expression data corresponding to the target virtual role.

[0079] Based on this, in the case that the target virtual role is a virtual image corresponding to a real person, the limb action data corresponding to the target virtual role can be determined by acquiring the data captured by the limb motion capture device. In addition, the facial expression data corresponding to the target virtual role can also be determined by acquiring the data collected by the facial expression capture device.

[0080] In the case that the target virtual role is a custom virtual image, the model data of the target virtual role can be generated by the application program for generating the virtual role.

[0081] Based on this, for the director operation event occurring in the performance process, the second director operation for the target virtual role can be performed in the performance process of the at least one target object based on the model data of the target virtual role; the second director operation includes role entry and / or role exit.

[0082] In the above embodiments, the model data of the target virtual role can be made before recording the performance behavior of the target object, so that the entry and / or exit of the target virtual role can be controlled based on the model data, thereby making the entry and / or exit operation of the target virtual role more concise and improving the efficiency of the role entry and / or exit. At the same time, the content of the generated target video can be enriched and the interactivity of the recorded performance data can be enhanced by performing the entry and / or exit operation of the target virtual role.

[0083] In an optional embodiment, since the event track data is data obtained after recording the director operation event in response to the director operation event occurring in the performance process. Therefore, the above editing of the recorded performance data based on the event track data to obtain the target video can also be understood as editing the director operation event based on the event track data to obtain the target video.

[0084] At this time, the above editing operation of the director operation event can be at least one of the following: event addition, event deletion, and event order adjustment.

[0085] In the case that the editing operation is "event addition", the event information and event occurrence time of the director operation event to be added can be determined, and the event information is added to the corresponding event occurrence time position.

[0086] In the case that the editing operation is "event deletion", the event information and event occurrence time of the director operation event to be deleted can be determined, and the event information at the position of the event occurrence time is deleted.

[0087] In the case that the editing operation is "event order adjustment", the initial event order of each director operation event included in the post-recording performance data can be determined first, and the event duration of each director operation event can be determined based on the event occurrence time of each director operation event. Then, the target event order of each director operation event after the event order adjustment can be determined, and each director operation event can be spliced based on the target event order and the event duration to obtain the post-recording performance data after the event order adjustment.

[0088] For example, assuming that the above editing process is "event addition", the event information of the director operation event to be added can be determined first, for example, the event information is "add performance behavior A of target object 1". At the same time, the event occurrence time of the director operation event to be added can also be determined, for example, the event occurrence time is 1 minute and 30 seconds. At this time, the performance behavior A of the target object 1 can be added at 1 minute and 30 seconds in the post-recording performance data, and then the target video can be obtained.

[0089] In the embodiments of the present disclosure, the director operation event that can be edited can be the first director operation performed on the scene element, can be the second director operation performed on the target virtual role, can be the event of adjusting the target object and / or the performance behavior of the target object in the performance process in S103, or can be a director operation event pre-stored in the database. At this time, the director operation event can be different from the director operation event occurring in the performance process.

[0090] In the above embodiments, the editing process of the director operation event on the post-recording performance data can be performed based on the event track data to realize the addition of events (or deletion of events, or adjustment of event order) in the post-recording performance data, so as to avoid the problem of resource waste caused by the need to re-record the performance behavior of the target object due to the adjustment of the director operation event. In addition, in the above embodiments, the way of generating the target video can also be expanded, which improves the diversity and flexibility of generating the target video.

[0091] In an optional embodiment, as shown in Figure 2 S105: editing the post-recording performance data to generate a target video, specifically including the following steps:

[0092] Step S21: editing the post-recording performance data to generate an initial video;

[0093] Step S22: performing a clipping process on the obtained initial video to obtain the target video.

[0094] As can be known from the above description, the post-recording performance data can include at least the following data: scene element data (for example, scene prop data, light data, scene special effect data, virtual lens), model data of a virtual character, event track data, and the like. At this time, the post-recording performance data can be edited based on the event track data to perform editing processing (for example, event addition, event deletion, event order adjustment) of the director operation, or the scene element data or the model data of the virtual character can be edited (for example, added or deleted) separately, and an initial video is generated after the processing.

[0095] After obtaining the initial video, the initial video can also be subjected to secondary editing processing (that is, the above-mentioned editing processing), and a target video is obtained after the processing. At this time, in one possible implementation, the initial video can be subjected to optimization processing by using a video editing software, and the optimization processing can be at least one of the following: picture optimization (for example, changing a filter), sound optimization (for example, noise reduction), content optimization (for example, adding a note, adding a subtitle), and the like. The disclosure does not make a specific limitation here, and any implementation that can be achieved is acceptable.

[0096] In the above-mentioned implementation, the initial video that meets the recording requirements more can be obtained by editing the post-recording performance data. Then, the optimized initial video (that is, the target video) can be obtained by editing the initial video, and this implementation not only improves the utilization rate of the initial video, but also improves the quality of the generated target video, and can better meet the user demand.

[0097] The implementation process of the video generation method provided in the embodiments of the disclosure will be described in detail below with reference to a flowchart.

[0098] As shown in Figure 3 , first, each scene element associated with the performance process of the target object is recorded to obtain recorded scene element data. Then, the performance behavior of at least one target object can be recorded to obtain post-recording performance data. At the same time, a director operation event occurring in the performance process can be recorded to obtain event track data.

[0099] Then, in one possible implementation, the post-recording performance data can be input into a video editor, and the post-recording performance data can be edited based on the event track data in the video editor to generate a first target video (that is, the target video as shown in Figure 3 ).

[0100] In another possible implementation, the post-recording performance data (or the above-mentioned first target video, that is, the target video as shown in Figure 3The initial video is input into a video editor for editing to obtain a second target video (i.e., as shown in FIG. 1C). Figure 3 The initial video is input into a video editor for editing to obtain a second target video (i.e., as shown in FIG. 1C).

[0101] Those skilled in the art can understand that, in the above method of the specific embodiment, the writing order of each step does not mean a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined according to its function and possible internal logic.

[0102] Based on the same inventive concept, the present embodiment also provides a video generation device corresponding to the video generation method. Since the principle of solving problems of the device in the present embodiment is similar to the above-mentioned video generation method of the present embodiment, the implementation of the device can be referred to the implementation of the method, and the repeated parts will not be described here.

[0103] Referring to Figure 4 FIG. 1A is a schematic diagram of a video generation device provided by the present embodiment, which comprises a recording unit 41, a response unit 42, and an editing unit 43.

[0104] The recording unit 41 is configured to record the performance behavior of the target object during the performance process of the at least one target object to obtain recorded performance data.

[0105] The response unit 42 is configured to record the director operation events occurring in the performance process to obtain event track data. The event track data records the event information and the event occurrence time of each director operation event.

[0106] The editing unit 43 is configured to edit the recorded performance data based on the event track data to generate a target video.

[0107] As described above, the director operation events occurring in the performance process can be recorded to obtain event track data, so that each director operation event in the performance process is independent of each other. Then, the recorded performance data can be edited based on the event track data, that is, any event information and event occurrence time in the performance process can be edited to edit the recorded performance data, thereby improving the flexibility and diversity of editing the recorded performance data.

[0108] In a possible implementation, the recording unit 41 is further configured to: before recording the performance behavior of the target object, record each scene element associated with the performance process respectively to obtain recorded scene element data; and the device is further configured to: based on the scene element data, perform the first director operation on the scene element in the performance process of the target object.

[0109] In a possible implementation, the device is further configured to: in the case where the scene element includes a scene prop, perform the first director operation on the scene element in the performance process of the target object according to the following steps: based on pre-recorded scene prop data, perform at least one of the following operations on the scene prop in the performance process of the at least one target object: adding, deleting, and pose adjustment.

[0110] In a possible implementation, the device is further configured to: in the case where the scene element includes light, perform the first director operation on the scene element in the performance process of the target object according to the following steps: based on pre-recorded various light data, perform a switching operation on the light in the scene in the performance process of the at least one target object.

[0111] In a possible implementation, the device is further configured to: in the case where the scene element includes a scene special effect, perform the first director operation on the scene element in the performance process of the target object according to the following steps: based on pre-recorded various special effect data, add a target scene special effect in the performance process of the target object.

[0112] In a possible implementation, the device is further configured to: in the case where the scene element includes a virtual lens, perform the first director operation on the scene element in the performance process of the target object according to the following steps: in the performance process of the at least one target object, switch the shooting angle of the virtual lens according to the current pose of the target object or a pre-set plot.

[0113] In a possible implementation, the device is further configured to: in the case where the at least one target object includes a target virtual role, generate model data of the target virtual role before recording the performance behavior of the target object; and based on the model data of the target virtual role, perform a second director operation on the target virtual role in the performance process of the at least one target object; the second director operation includes: role entry and / or role exit.

[0114] In a possible implementation, the editing unit 43 is further configured to: based on the event track data, perform at least one of the following operations on the director operation event of the recorded performance data: event addition, event deletion, and event order adjustment.

[0115] In one possible implementation, the editing unit 43 is further configured to: edit the recorded performance data to generate an initial video; and perform editing processing on the obtained initial video to obtain the target video.

[0116] The processing flow of each module in the device and the interaction flow between each module can be referred to the relevant descriptions in the above method embodiments, and will not be detailed here.

[0117] Corresponding to Figure 1 In the video generation method described in this disclosure, a computer device 500 is also provided, such as... Figure 5 The diagram shown is a structural schematic of a computer device 500 provided in an embodiment of this disclosure, including:

[0118] The system includes a processor 51, a memory 52, and a bus 53. The memory 52 stores execution instructions and includes main memory 521 and external memory 522. The main memory 521, also called internal memory, temporarily stores the processing data in the processor 51, as well as data exchanged with external memory such as a hard disk. The processor 51 exchanges data with the external memory 522 through the main memory 521. When the computer device 500 is running, the processor 51 communicates with the memory 52 through the bus 53, causing the processor 51 to execute the following instructions:

[0119] During the performance of at least one target object, the performance behavior of the target object is recorded to obtain the recorded performance data.

[0120] In response to the director operation events that occur during the performance, the director operation events are recorded to obtain event track data; the event track data records the event information and the event occurrence time of each director operation event;

[0121] Based on the event trajectory data, the recorded performance data is edited to generate the target video.

[0122] This disclosure also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the video generation method described in the above method embodiments. The storage medium can be a volatile or non-volatile computer-readable storage medium.

[0123] This disclosure also provides a computer program product carrying program code. The program code includes instructions that can be used to execute the steps of the video generation method described in the above method embodiments. For details, please refer to the above method embodiments, which will not be repeated here.

[0124] The computer program product can be implemented by hardware, software or a combination thereof. In an optional embodiment, the computer program product is embodied in a computer storage medium. In another optional embodiment, the computer program product is embodied in a software product, such as a software development kit (SDK) or the like.

[0125] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system and device described above can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here. In several embodiments provided in the present disclosure, it should be understood that the disclosed system, device and method can be implemented in other ways. The device embodiments described above are merely schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be omitted or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some communication interfaces, devices or units, which can be electrical, mechanical or other forms.

[0126] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place or distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0127] In addition, each functional unit in each embodiment of the present disclosure can be integrated in one processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit.

[0128] If the functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a nonvolatile computer readable storage medium executable by a processor. Based on this understanding, the technical solutions of the present disclosure essentially or the part that contributes to the prior art or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present disclosure. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (Read-Only Memory, ROM), a random access memory (Random Access Memory, RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0129] Finally, it should be noted that: the above-described embodiments are only specific embodiments of the present disclosure, used to illustrate the technical solutions of the present disclosure, and not to limit them. The protection scope of the present disclosure is not limited thereto. Although the present disclosure has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art who is familiar with the technology in the art can still make modifications or easily think of changes to the technical solutions described in the foregoing embodiments, or make equivalent replacements to some of the technical features; and these modifications, changes or replacements do not cause the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure, and should be covered within the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be subject to the protection scope of the claims.

Claims

1. A method of video generation, the method comprising: The method comprises the following steps: recording each scene element associated with the performance process to obtain recorded scene element data; recording the performance behavior of the target object during the performance process of the at least one target object to obtain recorded performance data; in response to a director operation event occurring in the performance process, recording the director operation event to obtain event track data; the event information and event occurrence time of each director operation event are recorded in the event track data; editing the recorded performance data based on the event track data to generate a target video.

2. The method of claim 1, wherein, The director operation event occurring in the performance process comprises a first director operation performed on the scene element in the performance process of the target object based on the scene element data.

3. The method of claim 2, wherein, The scene element comprises a scene prop. The first director operation performed on the scene element in the performance process of the target object comprises at least one of the following operations performed on the scene prop in the performance process of the at least one target object based on pre-recorded scene prop data: adding, deleting or adjusting the pose of the scene prop.

4. The method of claim 2, wherein, The scene element comprises light. The first director operation performed on the scene element in the performance process of the target object comprises a switching operation performed on the light in the scene in the performance process of the at least one target object based on pre-recorded light data of different types. The scene element comprises a scene special effect.

5. The method of claim 2, wherein, The first director operation performed on the scene element in the performance process of the target object comprises adding a target scene special effect in the performance process of the target object based on pre-recorded special effect data of different types. The scene element comprises a virtual lens. The first director operation performed on the scene element in the performance process of the target object comprises switching the shooting angle of the virtual lens according to the current pose of the target object or a pre-set plot in the performance process of the at least one target object.

6. The method of claim 2, wherein, The at least one target object comprises a target virtual character. Before recording the performance behavior of the target object, the method further comprises generating model data of the target virtual character. The director operation event occurring in the performance process comprises a second director operation performed on the target virtual character in the performance process of the at least one target object based on the model data of the target virtual character; the second director operation comprises character entry and / or character exit.

7. The method of claim 1, wherein, The editing of the recorded performance data based on the event track data to generate a target video comprises at least one of the following operations: adding, deleting or adjusting the order of the director operation event based on the event track data. The editing of the recorded performance data to generate a target video comprises the following steps:

8. The method of claim 1, wherein, editing the recorded performance data to generate an initial video; performing editing processing on the obtained initial video to obtain the target video.

9. The method according to any one of claims 1 to 8, characterized in that, The method comprises the following steps: a scene element recording unit is configured to record each scene element associated with the performance process to obtain recorded scene element data; ​ 10. A video generating apparatus characterized by comprising: ​ ​ A recording unit configured to record performance behavior of a target object during a performance of the target object to obtain recorded performance data; A response unit configured to record a director operation event occurring during the performance in response to the director operation event to obtain event track data; Event information and event occurrence time of each of the director operation events are recorded in the event track data; An editing unit configured to edit the recorded performance data based on the event track data to generate a target video.

11. A computer device, comprising: Comprise: A processor, a memory and a bus, the memory stores machine readable instructions executable by the processor, when the computer device is running, the processor and the memory communicate through the bus, the machine readable instructions are executed by the processor to execute the steps of the video generation method in any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, the computer program is executed by the processor to execute the steps of the video generation method in any one of claims 1 to 9.

Images