A fundamental problem in computer vision is that of inferring the intrinsic, 3D structure of the
world from flat, 2D images of that world. Traditional methods for recovering scene properties …

We present SIRFS (shape, illumination, and reflectance from shading), the first unified model
for recovering shape, chromatic illumination, and reflectance from a single image. Our model …

Existing shape-from-shading algorithms assume constant reflectance across the shaded
surface. Multi-colored surfaces are excluded because both shading and reflectance affect …

In many situations the reflectance function of a surface is approximately linear, and there is
an effielent closed-form solution to the shape-from-shading problem. When boundary …

Mutual illumination forms a significant component of image radiance that is not modeled by
the image irradiance equation. Its effects, which are easy to observe in real scenes, lead to …

Extracting surface orientation and surface depth from a shaded image is one of the classic
problems in computer vision. Many previous algorithms either violate integrability, ie, the …

Local analysis of image shading, in the absence of prior knowledge about the viewed scene,
may be used to provide information about the scene. The following has been proved. Every …

We develop a framework for extracting a concise representation of the shape information
available from diffuse shading in a small image patch. This produces a mid-level scene …

Estimation of illuminant direction, albedo, and shape from shading Page 58 Estimation of
Illuminant Direction, Albedo, and Shape from Shading 39 Estimation of Illuminant Direction …

Estimating surface normals from just a single image is challenging. To simplify the problem,
previous work focused on special cases, including directional lighting, known reflectance …