Apparatus, method and computer program for rendering a visual scene

A non-transitory digital storage medium having a computer program stored thereon for causing a computer to execute a method for rendering a visual scene, said method comprising:

• acquiring as a first input a set of images of one or more objects, and acquiring as a second input a geometry representation of the one or more objects in a 3D-space, the geometry representation comprising a position information of the one or more objects within the visual scene, wherein the set of images is based on a light field representation of the one or more objects and wherein at least one of the set of images comprises an image texture information and an image depth information,
• acquiring a final image representing the visual scene from a perspective of a target position, the visual scene comprising the one or more objects, and
• considering at least one of a lighting effect and/or an object interaction effect between the one or more objects and one or more further objects comprised by the visual scene,
• wherein the method further comprises:
• synthesizing a target view image from the set of images irrespective of the geometry representation, the target view image representing the one or more objects from the perspective of the target position, and
• mapping the target view image on the geometry representation under consideration of the target position.

Apparatus for rendering a visual scene, the apparatus comprising:

• a content visualization stage configured to
• acquire as a first input a set of images of one or more objects, and to acquire as a second input a geometry representation of the one or more objects in a 3D-space, the geometry representation comprising a position in-formation of the one or more objects within the visual scene,
• acquire a final image representing the visual scene from a perspective of a target position, the visual scene comprising the one or more objects, and
• consider at least one of a lighting effect and/or an object interaction effect between the one or more objects and one or more further objects comprised by the visual scene,
• wherein the content visualization stage comprises:
• a target view synthesis stage configured to acquire a target view image from the set of images irrespective of the geometry representation, the target view image representing the one or more objects from the perspective of the target position, and
• a texture mapping block being configured to map the target view image on the geometry representation under consideration of the target position,
• wherein the apparatus is implemented by a hardware apparatus,
• wherein the target view image comprises a target view texture information and a target view depth information, and
• wherein the texture mapping block is configured to use the target view depth information for selecting a point of the geometry representation on which a point of the target view image is mapped.

Apparatus for rendering a visual scene, the apparatus comprising a processor that is configured to perform a content visualization stage, wherein in the content visualization stage, the processor is configured to

• acquire as a first input a set of images of one or more objects, and to acquire as a second input a geometry representation of the one or more objects in a 3D-space, the geometry representation comprising a position information of the one or more objects within the visual scene, wherein the set of images is based on a light field representation of the one or more objects and wherein at least one of the set of images comprises an image texture information and an image depth information,
• acquire a final image representing the visual scene from a perspective of a target position, the visual scene comprising the one or more objects, and
• consider at least one of a lighting effect and/or an object interaction effect between the one or more objects and one or more further objects comprised by the visual scene,
• wherein the content visualization stage comprises:
• a target view synthesis stage configured to acquire a target view image from the set of images irrespective of the geometry representation, the target view image representing the one or more objects from the perspective of the target position, and
• a texture mapping block being configured to map the target view image on the geometry representation under consideration of the target position.