Abstract: A method including capturing a first plurality of images that include a foreground object and a background, capturing a second plurality of images that include the background, generating an alpha matte based on the first plurality of images and the second plurality of images using a trained machine learned model trained using a loss function configured to cause the trained machine learned model to learn high-frequency details of the foreground object, generating a foreground object image based on the first plurality of images and the second plurality of images using the trained machine learned model, and synthesizing an image including the foreground object image and a second background scene using the alpha matte.

Abstract: According to an aspect, a method includes generating at least one surface for a subject based on image data, the image data comprising a first image from a first perspective and a second image from a second perspective. The method further includes identifying a distribution of light intensity over the at least one surface and identifying a view independent feature based on the distribution of light intensity. The method also provides generating a texture map for a sequence of images based on the view independent feature.

Abstract: According to an aspect, a method includes generating at least one surface for a subject based on image data, the image data comprising a first image from a first perspective and a second image from a second perspective. The method further includes identifying a distribution of light intensity over the at least one surface and identifying a view independent feature based on the distribution of light intensity. The method also provides generating a texture map for a sequence of images based on the view independent feature.

Abstract: A method including capturing a first plurality of images that include a foreground object and a background, capturing a second plurality of images that include the background, generating an alpha matte based on the first plurality of images and the second plurality of images using a trained machine learned model trained using a loss function configured to cause the trained machine learned model to learn high-frequency details of the foreground object, generating a foreground object image based on the first plurality of images and the second plurality of images using the trained machine learned model, and synthesizing an image including the foreground object image and a second background scene using the alpha matte.

Abstract: A method including determining a viewpoint, generating a first image using an image generator, the first image including an object in a first orientation based on the viewpoint, modifying the image generator based on a second orientation of the object, and generating a second image based on the first image using the modified image generator.

Abstract: A method comprises receiving a first sequence of images of a portion of a user, the first sequence of images being monocular images; generating an avatar based on the first sequence of images, the avatar being based on a model including a feature vector associated with a vertex; receiving a second sequence of images of the portion of the user; and based on the second sequence of images, modifying the avatar with a displacement of the vertex to represent a gesture of the avatar.

Abstract: A method including selecting a first point from a 3D model representing an avatar, the first point being associated with an eye, selecting a second point from the 3D model, the second point being associated with a periocular region associated with the eye, generating an albedo and spherical harmonics (SH) coefficients based on the first point and the second point, and generating an image point based on the albedo, and the SH coefficients.

Abstract: Techniques include introducing a neural generator configured to produce novel faces that can be rendered at free camera viewpoints (e.g., at any angle with respect to the camera) and relit under an arbitrary high dynamic range (HDR) light map. A neural implicit intrinsic field takes a randomly sampled latent vector as input and produces as output per-point albedo, volume density, and reflectance properties for any queried 3D location. These outputs are aggregated via a volumetric rendering to produce low resolution albedo, diffuse shading, specular shading, and neural feature maps. The low resolution maps are then upsampled to produce high resolution maps and input into a neural renderer to produce relit images.

Abstract: Methods, systems, and media for relighting images using predicted deep reflectance fields are provided.

Abstract: Methods, systems, and media for relighting images using predicted deep reflectance fields are provided.