Shadow generation

An apparatus of shadow generation, comprising processing circuitry configured to:

• obtain light source information of a virtual light source and one or more observation parameters of a virtual camera, the light source information indicating an illumination effect of the virtual light source in a virtual scene, and the one or more observation parameters defining a field-of-view range of the virtual camera in the virtual scene with a three-dimensional model;
• generate, based on the light source information and the one or more observation parameters, a multi-angle contour map of the three-dimensional model, the multi-angle contour map being a combination of a plurality of binary contour images of the three-dimensional model from different angles;
• project, based on the light source information and the one or more observation parameters, the multi-angle contour map onto a reference plane, to obtain a hard shadow image of the three-dimensional model;
• obtain a shadow feature of the three-dimensional model based on the light source information and a material attribute of the three-dimensional model;
• and
• input the hard shadow image and the shadow feature into a convolutional neural network-based shadow prediction model that has been trained to cause the convolutional neural network-based shadow prediction model to output a soft shadow image of the three-dimensional model.

A non-transitory computer-readable storage medium storing instructions which when executed by a processor cause the processor to perform:

• obtaining light source information of a virtual light source and one or more observation parameters of a virtual camera, the light source information indicating an illumination effect of the virtual light source in a virtual scene, and the one or more observation parameters defining a field-of-view range of the virtual camera in the virtual scene with a three-dimensional model;
• generating, based on the light source information and the one or more observation parameters, a multi-angle contour map of the three-dimensional model, the multi-angle contour map being a combination of a plurality of binary contour images of the three-dimensional model from different angles;
• projecting, based on the light source information and the one or more observation parameters, the multi-angle contour map onto a reference plane, to obtain a hard shadow image of the three-dimensional model;
• obtaining a shadow feature of the three-dimensional model based on the light source information and a material attribute of the three-dimensional model;
• and
• inputting the hard shadow image and the shadow feature into a convolutional neural network-based shadow prediction model that has been trained to cause the convolutional neural network-based shadow prediction model to output a soft shadow image of the three-dimensional model.