3D object composition as part of a 2D digital image through use of a visual guide
Techniques and systems are described in which a visual guide is employed as part of an image processing system to aid composition of a 3D object as part of a digital image. In one example, the image processing system receives inputs that specify an orientation of a plane in the user interface. In response, the image processing system outputs the visual guide in the user interface as corresponding to the plane. The image processing system then orients a 3D object based on the plane defined by the visual guide, to which, rendering techniques are then applied such as physics-based rendering and image-based lighting.
1. In a digital medium environment to perform composition of a three-dimensional (3D) object as part of a two-dimensional digital image, a method implemented by at least one computing device, the method comprising:
receiving, by the at least one computing device, inputs in relation to the two-dimensional digital image;
defining, by the at least one computing device, rays corresponding to each respective input that radiate from an estimated camera position and pass through a point corresponding to the respective input;
determining, by the at least one computing device, a plane in relation to the inputs based on the rays and an orthogonality condition, the plane determined when an orthogonality error and a planarity error are below a threshold value;
outputting, by the at least one computing device, a visual guide in a user interface, the visual guide indicating the plane in conjunction with the two-dimensional digital image;
determining, by the at least one computing device, an orientation of the 3D object based on 3D coordinates of the plane of the visual guide; and
displaying, by the at least one computing device, the 3D object at the orientation in conjunction with the two-dimensional digital image in the user interface.
2. The method as described in claim 1 , wherein the inputs are input manually through user interaction with the user interface.
3. The method as described in claim 2 , wherein the inputs specify four corners of the plane in relation to the two-dimensional digital image in the user interface.
4. The method as described in claim 2 , wherein the inputs define the plane through entry in defined order.
5. The method as described in claim 2 , wherein the plane is determined based on a permutation of a plurality of possible permutations of the user inputs that introduces the least amount of error.
6. The method as described in claim 1 , wherein the inputs are generated automatically and without user intervention.
7. The method as described in claim 6 , wherein the inputs are generated automatically and without user intervention through edge or corner detection techniques involving at least one object in the two-dimensional digital image.
8. The method as described in claim 1 , further comprising receiving, by the at least one computing device, an input to modify the visual guide via user interaction with the visual guide via the user interface and wherein the determining the orientation is based at least in part on the receiving of the input and wherein the input to modify is configured to resize, update, slide, or lift the visual guide with respect to the two-dimensional digital image.
9. The method as described in claim 1 , further comprising generating, by the at least one computing device, the visual guide based on the inputs.
10. The method as described in claim 9 , wherein the generating is based at least in part on a known camera projection model.
11. The method as described in claim 9 , wherein the generating is based at least in part on a depth calculated using at least the inputs.
12. In a digital medium environment to perform composition of a three-dimensional (3D) object as part of a two-dimensional digital image, a system comprising:
an orientation input module implemented at least partially in hardware of at least one computing device to:
receive inputs in relation to the two-dimensional digital image;
define rays corresponding to each respective input that radiate from an estimated camera position and pass through a point corresponding to the respective input; and
determine a plane in relation to the inputs based on the rays and an orthogonality condition, the plane determined when an orthogonality error and a planarity error are below a threshold value;
a visual guide generation module implemented at least partially in hardware of at least one computing device to generate and output a visual guide indicating the plane in conjunction with the two-dimensional digital image in a user interface; and
a three-dimensional (3D) object placement module to orient the 3D object in the user interface as displayed in conjunction with the two-dimensional digital image based on 3D coordinates of the plane of the visual guide.
13. The system as described in claim 12 , wherein the visual guide generation module further includes a visual guide modification module configured to modify the visual guide in response to an input received via the user interface.
14. The system as described in claim 13 , wherein the visual guide generation module is configured to resize, update, slide, or lift the visual guide with respect to the two-dimensional digital image in the user interface.
15. The system as described in claim 12 , wherein the visual guide generation module is configured to generate the visual guide based at least in part on a known camera projection model.
16. The system as described in claim 12 , wherein the visual guide generation module is configured to generate the visual guide based at least in part on a depth calculated using at least one of the inputs defining the plane.
17. The system as described in claim 12 , wherein the inputs specify four corners of the plane in relation to the two-dimensional digital image in the user interface through entry in a defined order.
18. The system as described in claim 12 , wherein the plane is defined based on a permutation of a plurality of possible permutations of the user inputs that introduces a least amount of error.
19. In a digital medium environment to perform composition of a 3D object as part of a 2D digital image, a system comprising:
means for receiving inputs in relation to the 2D digital image;
means for defining rays corresponding to each respective input that radiate from an estimated camera position and pass through a point corresponding to the respective input;
means for determining a plane in relation to the inputs based on the rays and an orthogonality condition, the plane determined when an orthogonality error and a planarity error are below a threshold value;
means for outputting a visual guide in a user interface, the visual guide indicating the plane in conjunction with the 2D digital image;
means for determining an orientation of the 3D object based on 3D coordinates of the plane of the visual guide; and
means for displaying the 3D object at the orientation in conjunction with the 2D digital image in the user interface.
20. The system as described in claim 19 , wherein the outputting means is configured to generate the visual guide based at least in part on a known camera projection mode or a known depth of at least one of the inputs defining the plane.