Techniques for improved lighting models for appearance capture

Improved lighting-model appearance-capture rendering technique (continuation).

Various embodiments include a system for rendering an object, such as human skin or a human head, from captured appearance data. The system includes a processor executing a near field lighting reconstruction module. The system determines at least one of a three-dimensional (3D) position or a 3D orientation of a lighting unit based on a plurality of captured images of a mirror sphere. For each point light source in a plurality of point light sources included in the lighting unit, the system determines an intensity associated with the point light source. The system determines captures appearance data of the object, where the object is illuminated by the lighting unit. The system renders an image of the object based on the appearance data and the intensities associated with each point light source in the plurality of point light sources.

BACKGROUND Field of the Various Embodiments (1) Various embodiments relate generally to appearance capture systems and, more specifically, to techniques for improved lighting models for appearance capture. Description of the Related Art (2) One aspect of rendering realistic human faces is to capture the appearance of the skin, which has a complex multi-layer structure with combined surface and subsurface reflectance properties. Appearance capture techniques estimate geometry and reflectance properties of various objects (such as a human head, facial skin, and/or the like) by performing a computationally intensive inverse rendering optimization in which one or more images are re-rendered a large number of times and compared to real images captured by multiple cameras at various positions and orientations. While state-of-the-art appearance capture techniques have achieved impressive results, such techniques often make simplifying assumptions that do not always hold in reality, even though these simplifying assumptions help to reduce computational complexity and rendering time. (3) One such simplifying assumption is that light sources are often modeled as a collection of point light sources (referred to as an environment map) that are distant from the face. The light rays from each of these light sources are, therefore, assumed to strike all points on the face at the same incident angle (direction). Further, the directional distribution of incoming light is assumed to be spatial