Disclosed herein is a web-based videoconference system that allows for video avatars to navigate within a virtual environment. Various methods for efficient modeling, rendering, and shading are disclosed herein.

There is provided an image generation device, an image generation method, and a program capable of observing any point on the ground from a free viewpoint in the sky at any time. The image generation device includes an image generation unit that generates a free viewpoint image of a predetermined point on the ground viewed from a predetermined virtual viewpoint in the sky using a 3D model of a stationary subject generated using a satellite image captured by an artificial satellite and dynamic subject identification information that identifies a dynamic subject. The present technology can be applied to, for example, an image generation device and the like that generate a free viewpoint image from a satellite image captured by an artificial satellite.

A design support apparatus includes an acquisition unit configured to acquire an electromagnetic wave image in which a captured image obtained by capturing an electronic device and a map obtained by mapping, in a two-dimensional space, a measurement result of an electromagnetic wave radiated from the electronic device are superimposed, and a composition unit configured to cause a display unit to display a CAD drawing representing a shape of the electronic device and the electromagnetic wave image in a superimposed manner such that the CAD drawing and a device image that is an image of the electronic device in the captured image are aligned.

A reduction in quality of a virtual viewpoint image is suppressed. An image processing apparatus specifies an image in which a specific position in a target object is not occluded by another object from among a plurality of images obtained by the plurality of imaging apparatuses based on a pixel value of the plurality of images; determines, based on the specified image, a value of a pixel corresponding to the specific position in the virtual viewpoint image to be generated based on the plurality of images; and generates the virtual viewpoint image including the target object based on the determined value of the pixel.

A method, performed by an electronic device, of generating a three-dimensional (3D) image, includes: obtaining a first image through a first camera of the electronic device and obtaining a second image through a second camera of the electronic device; obtaining depth information of a pixel included in the first image; identifying, based on the depth information, a first layer image and a second layer image from the first image; inpainting, based on the first image and the second image, at least a part of the first layer image; and generating, based on the second layer image and the inpainted first layer image, the 3D image including a plurality of layers.

The present disclosure relates to an image processing apparatus and method that can prevent an increase in the load of a decoding process for encoded data in a point cloud video-based approach. The parameters related to a plurality of point cloud models of a point cloud are transformed, a two-dimensional plane image onto which the plurality of point cloud models having the transformed parameters is projected is encoded, and a bitstream containing encoded data of the two-dimensional image and transform information that is information regarding the transform of the parameters is generated. The present disclosure can be applied to an information processing device, an image processing apparatus, an electronic apparatus, an information processing method, a program, or the like, for example.

A system and method for hologram synthesis and processing capable of synthesizing holographic 3D data and displaying (or reconstructing) a full 3D image at high speed using a deep learning engine. The system synthesizes or generates a digital hologram from a light field refocus image input using the deep learning engine. That is, RGB-depth map data is acquired at high speed using the deep learning engine, such as a convolutional neural network (CNN), from real 360° multi-view color image information and the RGB-depth map data is used to produce hologram content. In addition, the system interlocks hologram data with user voice recognition and gesture recognition information to display the hologram data at a wide viewing angle and enables interaction with the user.

Methods and/or apparatus provide for obtaining intrinsics and extrinsics of a plurality of cameras arranged to capture a scene and based thereon, generate a voxel representation of the scene; obtaining extrinsics and intrinsics of a virtual camera; mapping the extrinsics and intrinsics of the virtual camera to at least one voxel surface defined in a data structure and to identify at least one camera pair suitable for obtaining depth data for that voxel surface based on the corresponding camera pair identifier; and receiving an input from the mapping unit, and in response obtaining images captured by the cameras in the at least one camera pair identified as being suitable for reconstructing the scene from the viewpoint of the virtual camera, and to generate an image of the scene from the viewpoint of the virtual camera based on the obtained images.

A virtual camera captures first images of a three-dimensional (3D) digital representation of a visual asset from different perspectives and under different lighting conditions. The first images are training images that are stored in a memory. One or more processors implement a generative adversarial network (GAN) that includes a generator and a discriminator, which are implemented as different neural networks. The generator generates second images that represent variations of the visual asset concurrently with the discriminator attempting to distinguish between the first and second images. The one or more processors update a first model in the discriminator and/or a second model in the generator based on whether the discriminator successfully distinguished between the first and second images. Once trained, the generator generates images of the visual asset based on the first model, e.g., based on a label or an outline of the visual asset.

A three-dimensional model distribution method includes generating a depth image from a three-dimensional model; and distributing the depth image and information for restoring the three-dimensional model from the depth image.