One-click filmmaking
A method and device for one-click filmmaking are provided. The method includes: obtaining a script from a user, detecting a single user operation, in response to the single user operation, obtaining a plurality of shots and estimating information of the plurality of shots based on the script, and automatically generating a film based on an auto-cinematography algorithm and the estimated information of the plurality of shots. The estimated information of one of the plurality of shots comprises at least one of a character of a shot, a scene of the shot, one or more positions of the character in the shot, a duration of the shot, or a shot type.
1. A method for one-click filmmaking, applied to a computing device, comprising:
obtaining a script from a user;
detecting a single user operation;
in response to the single user operation, obtaining a plurality of shots and estimating information of the plurality of shots based on the script, the estimated information of one of the plurality of shots comprising at least one of a character of a shot, a scene of the shot, one or more positions of the character in the shot, a duration of the shot, or a shot type, and estimating the information of the plurality of shots based on the script including:
estimating the duration of one of the plurality of shots based on the script, including:
deriving the duration of the one of the plurality of shots based on at least one of a length of a dialogue in the script, a distance of a movement of the character, or a time length of an action in the script; and
automatically generating a film based on an auto-cinematography algorithm and the estimated information of the plurality of shots.
2. The method according to claim 1 , wherein estimating the information of the plurality of shots further includes automatically configuring the shot type of one of the plurality of shots based on a deep learning algorithm.
3. The method according to claim 1 , further comprising, before automatically generating the film:
displaying the information estimated of one of the plurality of shots to the user; and
receiving a user confirmation operation for the information estimated.
4. The method according to claim 3 , further comprising, before receiving the user confirmation operation for the information estimated:
receiving a user adjustment operation for the information estimated.
5. The method according to claim 1 , further comprising, after automatically generating the film:
requesting a user selection on whether to play the film generated; and
in response to determining to play the film, playing the film to the user.
6. The method according to claim 1 , further comprising, after automatically generating the film:
requesting a user selection on whether the film generated is approved;
in response to determining the film is not approved, displaying information estimated of one of the plurality of shots to the user;
receiving a user adjustment operation for the information estimated; and
automatically generating an updated film based on the adjusted information and the auto-cinematography algorithm.
7. The method according to claim 1 , wherein obtaining the script from the user includes at least one of:
receiving a screenplay uploaded by the user;
receiving a text script input by the user; or
receiving a voice input from the user and converting the voice input into text using automatically speech recognition (ASR).
8. The method according to claim 1 , wherein the script is analyzed with natural language processing (NLP) techniques.
9. The method according to claim 1 , wherein estimating the information of the plurality of shots further includes: for one of the plurality of shots,
estimating the character of the shot based on the script including finding, from a library, a candidate character matching a description of the character of the shot in the script; and
estimating the scene of the shot based on the script including finding, from the library, a candidate scene matching a description of the scene of the shot in the script.
10. A device for one-click filmmaking, comprising:
a memory; and
a processor coupled to the memory and configured to perform a plurality of operations comprising:
obtaining a script from a user;
detecting a single user operation;
in response to the single user operation, obtaining a plurality of shots and estimating information of the plurality of shots based on the script, the estimated information of one of the plurality of shots comprising at least one of a character of a shot, a scene of the shot, one or more positions of the character in the shot, a duration of the shot, or a shot type, and estimating the information of the plurality of shots based on the script including:
estimating the duration of one of the plurality of shots based on the script, including:
deriving the duration of the one of the plurality of shots based on at least one of a length of a dialogue in the script, a distance of a movement of the character, or a time length of an action in the script; and
automatically generating a film based on an auto-cinematography algorithm and the estimated information of the plurality of shots.
11. The device according to claim 10 , wherein estimating the information of the plurality of shots further comprises:
automatically configuring the shot type of one of the plurality of shots based on a deep learning algorithm.
12. The device according to claim 10 , wherein the plurality of operations performed by the processor further comprises, before automatically generating the film:
displaying the information estimated of one of the plurality of shots to the user; and
receiving a user confirmation operation for the information estimated.
13. The device according to claim 12 , wherein the plurality of operations performed by the processor further comprises, before receiving the user confirmation operation for the information estimated:
receiving a user adjustment operation for the information estimated.
14. The device according to claim 10 , wherein the plurality of operations performed by the processor further comprises, after automatically generating the film:
requesting a user selection on whether to play the film generated; and
in response to determining to play the film, playing the film to the user.
15. The device according to claim 10 , wherein the plurality of operations performed by the processor further comprises, after automatically generating the film:
requesting a user selection on whether the film generated is approved;
in response to determining the film is not approved, displaying the information estimated of one of the plurality of shots to the user;
receiving a user adjustment operation for the information estimated; and
automatically generating an updated film based on the adjusted information and the auto-cinematography algorithm.
16. The device according to claim 10 , wherein obtaining the script from the user includes at least one of:
receiving a screenplay uploaded by the user;
receiving a text script input by the user; or
receiving a voice input from the user and converting the voice input into text using automatically speech recognition (ASR).
17. The device according to claim 10 , wherein the script is analyzed with natural language processing (NLP) techniques.
18. The device according to claim 10 , wherein estimating the information of the plurality of shots further includes: for one of the plurality of shots,
estimating the character of the shot based on the script including finding, from a library, a candidate character matching a description of the character of the shot in the script; and
estimating the scene of the shot based on the script including finding, from the library, a candidate scene matching a description of the scene of the shot in the script.