Deep spectral reflectance and illuminant estimation from self-interreflections

Spectral reflectance estimation from one RGB image using self-interreflections in a concave object

Light interreflections occurring in a concave object generate a color gradient which is characteristic of the object’s spectral reflectance. In this paper, we use this property in order to estimate the spectral reflectance of matte, uniformly colored, V-shaped surfaces from a single RGB image taken under directional lighting. First, simulations show that using one image of the concave object is...

Standard surface-reflectance model and illuminant estimation

In the standard reflectance model for inhomogeneous materials it is assumed that light is reflected by two independent mechanisms. One component is reflected at the interface of the material and air. Light reflected by this mechanism does not interact with surface colorant, and its spectral composition is assumed to equal that of the incident light. The second component is reflected after enter...

Dense Estimation of Surface Reflectance Properties of Objects with Interreflections

In augmented virtuality which virtualizes real objects to construct a mixed reality environment, it is important to estimate object surface reflectance properties to render objects under arbitrary illumination conditions. The authors developed a method to estimate reflectance properties of object surfaces densely. However, it was difficult to estimate surface reflectance properties faithfully f...

Deep Specialized Network for Illuminant Estimation

Illuminant estimation to achieve color constancy is an illposed problem. Searching the large hypothesis space for an accurate illuminant estimation is hard due to the ambiguities of unknown reflections and local patch appearances. In this work, we propose a novel Deep Specialized Network (DS-Net) that is adaptive to diverse local regions for estimating robust local illuminants. This is achieved...

Deep Specialized Network for Illuminant Estimation Supplemental Material