Figure 2. Overview of our method. The feature extractor network G produces pixel-aligned features z from an input image I for all points
x
in space x. The implicit signed distance function network f computes the distance d to the closest surface given a point and its feature.
Additionally f returns albedo colors a defined for surface points. The shading network s predicts the shading for surface points given its
surface normal n , as well as illumination l. On the right we show the reconstruction of geometry and albedo colors, and the shaded 3D
x
geometry.