Methods and systems disclosed herein relate generally to surface-rendering neural networks to represent and render a variety of material appearances (e.g., textured surfaces) at different scales. The system includes receiving image metadata for a texel that includes position, incoming and outgoing radiance direction, and a kernel size. The system applies a offset-prediction neural network to the query to identify an offset coordinate for the texel. The system inputs the offset coordinate to a data structure to determine a feature vector for the texel of the textured surface. The reflectance feature vector is then processed using a decoder neural network to estimate a light-reflectance value of the texel, at which the light-reflectance value is used to render the texel of the textured surface.

A method for simulating, at an instant, the illumination of an indoor scene observed by a camera and being illuminated by outdoor light, the method comprising: a first preliminary phase including: obtaining a reflectance map of the scene elaborating normalized radiosity maps for the contribution of the sky and the ground, a second phase carried out within a first given duration from the instant including: obtaining the position of the sun, obtaining a normalized radiosity map for the contribution of the sun, a third phase, including: acquiring an image of the scene, determining brightness scale parameters for the ground, the sky, and the sun. The disclosure also proposes tracking the camera position.

Implementations of the subject technology relate to generative scene networks (GSNs) that are able to generate realistic scenes that can be rendered from a free moving camera at any location and orientation. A GSN may be implemented using a global generator and a locally conditioned radiance field. GSNs may employ a spatial latent representation as conditioning for a grid of locally conditioned radiance fields, and may be trained using an adversarial learning framework. Inverting a GSN may allow free navigation of a generated scene conditioned on one or more observations.

Implementations of the subject technology relate to generative scene networks (GSNs) that are able to generate realistic scenes that can be rendered from a free moving camera at any location and orientation. A GSN may be implemented using a global generator and a locally conditioned radiance field. GSNs may employ a spatial latent representation as conditioning for a grid of locally conditioned radiance fields, and may be trained using an adversarial learning framework. Inverting a GSN may allow free navigation of a generated scene conditioned on one or more observations.

An exemplary object modeling system determines a set of directional occlusion values associated with a surface point on a surface of a virtual object. The directional occlusion values are representative of an exposure of the surface point to ambient light from each direction of a set of directions defined by a radiosity basis. The object modeling system also stores the set of directional occlusion values as part of texture data defining the surface point and provides the texture data that includes the set of stored directional occlusion values associated with the surface point. Corresponding methods and systems are also disclosed.

Disclosed is a method to derive the absorption coefficient, transparency, and/or the scattering coefficient from the user-specified parameters including roughness, phase function, index of refraction (IOR), and color by performing the simulation once, and storing the results of the simulation in an easy to retrieve representation, such as a lookup table, or an analytic function. To create the analytic function, one or more analytic functions can be fitted to the results of the simulation for the multiple parameters including roughness, phase function, IOR, and color. The lookup table can be combined with the analytic representation. For example, the lookup table can be used to represent the color, roughness, and phase function, while the IOR can be represented by an analytic function. For example, when the IOR is above 2, the lookup table becomes three-dimensional and the IOR is calculated using the analytic function.

The present invention relates to the importance-directed geometric simplification of complex mesh-based representations of objects in virtual environments for radiosity-based global illumination simulations. By means of simplification, the time needed to solve the radiosity equation and so generate an accurate physically-based simulation can be markedly reduced. Further, geometric simplification is performed during the global illumination simulation process rather than as a preprocess step.

The present invention relates to the importance-directed geometric simplification of complex mesh-based representations of objects in virtual environments for radiosity-based global illumination simulations. By means of simplification, the time needed to solve the radiosity equation and so generate an accurate physically-based simulation can be markedly reduced. Further, geometric simplification is performed during the global illumination simulation process rather than as a preprocess step.

The present disclosure provides a light field imaging system by projecting near-infrared spot in remote sensing based on a multifocal microlens array. The light field imaging system includes a near-infrared spot projection apparatus (100) and a light field imaging component (200), where the near-infrared spot projection apparatus (100) is configured to scatter near-infrared spots on a to-be-observed object to add texture information to a target image, and the light field imaging component (200) is configured to image a target scene light ray with additional texture information. The present disclosure can extend a target depth-of-field (DOF) detection range, and particularly, reconstruct a surface of a weak-texture object.

A measurement apparatus is provided which includes a wafer stage having an upper surface on which a wafer to be measured is placed; a light source capable of illuminating the upper surface with predetermined light; a light detection portion configured to take an image of the wafer illuminated with the predetermined light by the light source; a polarization element provided between the light source and the wafer stage, or between the wafer stage and the light detection portion; and a controller. The controller takes a difference value between two signals that are obtained based on corresponding types of polarization states, in each of which a first and second element of a Stokes Vector are same, and thus measures an asymmetric structure within the wafer, based on the difference value.