Rendering of Cast Shadows

Appearance-based approaches have the advantage of representing the variability of an object’s appearance due to illumination change without explicit shape modeling. While a substantial amount of research has been performed on the representation of object’s diffuse and specular shading, little attention has been paid to cast shadows which are critical for attaining realism when multiple objects are present in a scene. We present an appearance-based method for representing shadows and rendering them in a 3D environment without explicit geometric modeling of shadow-casting object. A cubemap-like illumination array is constructed, and an object’s shadow under each cubemap light pixel is sampled on a plane. Only the geometry of the shadow-sampling plane is known relative to the cubemap lighting. The sampled images of both the object and its cast shadows are represented using the Haar wavelet, and rendered on an arbitrary 3D background of known geometry. Experiments are carried out to demonstrate the effectiveness of the presented method.