A method, a system, a device, and a computer readable storage medium for video reconstruction are disclosed. The method includes: obtaining an image combination of multi-angle free-perspective video frames, parameter data corresponding to the image combinations of the video frames, and position information of a virtual viewpoint based on a user interaction; selecting texture images and depth maps of corresponding groups in the image combinations of the video frames at a time moment of the user interaction according to a preset rule and based on the position information of the virtual viewpoint and the parameter data corresponding to the image combinations of the video frames; and combining and rendering the texture images and the depth maps of the corresponding groups based on the position information of the virtual viewpoint and parameter data corresponding to the depth maps and the texture images of the corresponding groups to obtain a reconstructed image.

A method, a system, a device, and a computer readable storage medium for video reconstruction are disclosed. The method includes: obtaining an image combination of multi-angle free-perspective video frames, parameter data corresponding to the image combinations of the video frames, and position information of a virtual viewpoint based on a user interaction; selecting texture images and depth maps of corresponding groups in the image combinations of the video frames at a time moment of the user interaction according to a preset rule and based on the position information of the virtual viewpoint and the parameter data corresponding to the image combinations of the video frames; and combining and rendering the texture images and the depth maps of the corresponding groups based on the position information of the virtual viewpoint and parameter data corresponding to the depth maps and the texture images of the corresponding groups to obtain a reconstructed image.

The invention relates to a solution wherein a bitstream defining a presentation is generated, the presentation comprising an omnidirectional visual media content and a first visual media component and a second visual media component; indicating in the bitstream a first presentation timeline associated with the first visual media component; indicating in the bitstream a second presentation timeline associated with the second visual media component; indicating in the bitstream a switching mode to a second presentation timeline associated with the second visual media component; and indicating in the bitstream, that the switching mode is with respect to the first presentation timeline or to the second presentation timeline.

The invention relates to a solution wherein a bitstream defining a presentation is generated, the presentation comprising an omnidirectional visual media content and a first visual media component and a second visual media component; indicating in the bitstream a first presentation timeline associated with the first visual media component; indicating in the bitstream a second presentation timeline associated with the second visual media component; indicating in the bitstream a switching mode to a second presentation timeline associated with the second visual media component; and indicating in the bitstream, that the switching mode is with respect to the first presentation timeline or to the second presentation timeline.

Viewpoint-related information is associated with a captured image, a plurality of viewpoint images, or a synthesized image, the captured image being generated by capturing an image of a subject with a single image sensor through a plurality of monocular optical systems with optical paths independent of each other, the plurality of viewpoint images being extracted from the captured image and having each of the plurality of monocular optical systems as a viewpoint, the synthesized image being obtained by synthesizing the plurality of viewpoint images respectively corresponding to the plurality of monocular optical systems, and the viewpoint-related information being used to specify a region of the plurality of viewpoint images in the captured image. The present disclosure is applicable to, for example, image-capturing apparatus, electronic devices, interchangeable lenses or camera systems in which a plurality of monocular lenses is extended, information processing methods, programs, or the like.

Viewpoint-related information is associated with a captured image, a plurality of viewpoint images, or a synthesized image, the captured image being generated by capturing an image of a subject with a single image sensor through a plurality of monocular optical systems with optical paths independent of each other, the plurality of viewpoint images being extracted from the captured image and having each of the plurality of monocular optical systems as a viewpoint, the synthesized image being obtained by synthesizing the plurality of viewpoint images respectively corresponding to the plurality of monocular optical systems, and the viewpoint-related information being used to specify a region of the plurality of viewpoint images in the captured image. The present disclosure is applicable to, for example, image-capturing apparatus, electronic devices, interchangeable lenses or camera systems in which a plurality of monocular lenses is extended, information processing methods, programs, or the like.

Viewpoint-related information is associated with a captured image, a plurality of viewpoint images, or a synthesized image, the captured image being generated by capturing an image of a subject with a single image sensor through a plurality of monocular optical systems with optical paths independent of each other, the plurality of viewpoint images being extracted from the captured image and having each of the plurality of monocular optical systems as a viewpoint, the synthesized image being obtained by synthesizing the plurality of viewpoint images respectively corresponding to the plurality of monocular optical systems, and the viewpoint-related information being used to specify a region of the plurality of viewpoint images in the captured image. The present disclosure is applicable to, for example, image-capturing apparatus, electronic devices, interchangeable lenses or camera systems in which a plurality of monocular lenses is extended, information processing methods, programs, or the like.

Viewpoint-related information is associated with a captured image, a plurality of viewpoint images, or a synthesized image, the captured image being generated by capturing an image of a subject with a single image sensor through a plurality of monocular optical systems with optical paths independent of each other, the plurality of viewpoint images being extracted from the captured image and having each of the plurality of monocular optical systems as a viewpoint, the synthesized image being obtained by synthesizing the plurality of viewpoint images respectively corresponding to the plurality of monocular optical systems, and the viewpoint-related information being used to specify a region of the plurality of viewpoint images in the captured image. The present disclosure is applicable to, for example, image-capturing apparatus, electronic devices, interchangeable lenses or camera systems in which a plurality of monocular lenses is extended, information processing methods, programs, or the like.

Mechanisms for generating compressed images are provided. More particularly, methods, systems, and media for capturing, reconstructing, compressing, and rendering view-dependent immersive light field video with a layered mesh representation are provided.

Mechanisms for generating compressed images are provided. More particularly, methods, systems, and media for capturing, reconstructing, compressing, and rendering view-dependent immersive light field video with a layered mesh representation are provided.