Environment map upscaling for digital image generation
Environment map upscaling techniques are described for digital image generation. A digital object and an environment map are received, the environment map defines lighting conditions within a panoramic view of an environment. A viewpoint is detected with respect to the panoramic view in the environment map. A map fragment is identified from the environment map based on the detected viewpoint and an upscaled map fragment is formed by upscaling the map fragment. A digital image is then generated based on the upscaled map fragment and the digital object as having the lighting conditions applied based on the environment map.
1 . A method implemented by a processing device, the method comprising:
receiving, by the processing device, a digital object and an environment map defining lighting conditions within a panoramic view of an environment;
receiving a user input as navigating to a view as displayed within a user interface of the environment as defined by the environment map;
detecting, by the processing device, a viewpoint with respect to the panoramic view in the environment map that corresponds to the view;
identifying, by the processing device, a map fragment from the environment map based on the detected viewpoint;
forming, by the processing device, an upscaled map fragment by upscaling the map fragment;
applying, by the processing device, at least one lighting condition to the digital object based on the lighting conditions defined by the environment map; and
generating, by the processing device, a digital image based on the upscaled map fragment and the digital object as having the at least one lighting condition, the digital object configured as a foreground layer and the upscaled map fragment configured as a background layer of the digital image.
2 . The method as described in claim 1 , wherein the upscaling is performed, at least in part, using machine learning through execution of a machine-learning model.
3 . The method as described in claim 2 , wherein the machine-learning model is a convolutional neural network.
4 . The method as described in claim 1 , wherein the upscaling is performed, at least in part, using bilinear interpolation, bicubic interpolation, or nearest-neighbor interpolation.
5 . The method as described in claim 1 , wherein the detecting is performed based on a visible portion of the environment map displayed in the user interface.
6 . The method as described in claim 1 , wherein the upscaled map fragment is configured as a two-dimensional digital image.
7 . The method as described in claim 1 , wherein the upscaled map fragment forms a background of the digital image and the digital object is positioned in a foreground of the digital image.
8 . The method as described in claim 1 , wherein the panoramic view supports a three-hundred-and-sixty-degree view of the digital object as disposed within the environment.
9 . The method as described in claim 1 , wherein the environment map defines the lighting conditions using a high dynamic range as part of an image-based lighting technique.
10 . A computing device comprising:
a processing device; and
a computer-readable storage medium storing instructions that, responsive to execution by the processing device, causes the processing device to perform operations including:
receiving a user input as navigating to a view as displayed within a user interface of an environment as defined by an environment map;
detecting a viewpoint, as displayed via the user interface, defined with respect to a three-dimensional environment as a visible portion of the environment map;
identifying a map fragment from an environment map based on the viewpoint, the environment map defining a three-dimensional environment and lighting conditions within the three-dimensional environment; and
generating a background of a two-dimensional digital image by upscaling the map fragment using a machine-learning model.
11 . The computing device as described in claim 10 , wherein the machine-learning model is a convolutional neural network.
12 . The computing device as described in claim 10 , wherein the upscaling is performed, at least in part, using bilinear interpolation, bicubic interpolation, or nearest-neighbor interpolation.
13 . The computing device as described in claim 10 , wherein the three-dimensional environment supports a three-hundred-and-sixty-degree view.
14 . The computing device as described in claim 10 , wherein the environment map defines lighting conditions using a high dynamic range (HDR) as part of an image-based lighting technique.
15 . The computing device as described in claim 10 , wherein a digital object is configured in a foreground as a foreground layer and the upscaled map fragment is configured as the background as a background layer of the two-dimensional digital image.
16 . One or more computer readable storage media storing instructions that, responsive to execution by a processing device, causes the processing device to perform operations including:
generating a background of a digital image, the generating including:
receiving a user input as navigating to a view as displayed within a user interface of an environment as defined by an environment map;
detecting a viewpoint with respect to a panoramic view in the environment map that corresponds to the view;
identifying a map fragment from the environment map based on a viewpoint detected with respect to an environment map, the environment map defining lighting conditions within an environment; and
forming an upscaled map fragment by upscaling the map fragment using a machine learning model;
generating a foreground of the digital image by applying at least one lighting condition to a digital object based on the lighting conditions defined by the environment map; and
outputting the digital image as including the foreground and the background.
17 . The one or more computer readable storage media as described in claim 16 , wherein the foreground is configured as a foreground layer and the background is configured as a background layer of the digital image.
18 . The one or more computer readable storage media as described in claim 16 , wherein the viewpoint is based on a visible portion of the environment map displayed in a user interface.
19 . The one or more computer readable storage media as described in claim 16 , wherein the environment map defines the lighting conditions in a high dynamic range (HDR) as part of an image-based lighting technique.
20 . The one or more computer readable storage media as described in claim 16 , wherein the digital object is configured as a foreground layer and the upscaled map fragment is configured as a background layer of the digital image.