Illumination Recovery From Image With Cast Shadows Via Sparse Representation

Abstract

Abstract-In this paper, we propose using sparse representation for recovering the illumination of a scene from a single image with cast shadows, given the geometry of the scene. The images with cast shadows can be quite complex and therefore cannot be well approximated by low-dimensional linear subspaces. However, it can be shown that the set of images produced by a Lambertian scene with cast shadows can be efficiently represented by a sparse set of images generated by directional light sources. We first model an image with cast shadows as composed of a diffusive part (without cast shadows) and a residual part that captures cast shadows. Then, we express the problem in an 1 -regularized least squares formulation, with nonnegativity constraints (as light has to be nonnegative at any point in space). This sparse representation enjoys an effective and fast solution, thanks to recent advances in compressive sensing. In experiments on both synthetic and real data, our approach performs favorably in comparison with several previously proposed methods.

Inverse Transport Networks

“…Physicsbased algorithms for recovering scene parameters conceptually comprise three steps: (i) formulate an approximate image formation (or forward rendering) model as a function of the scene parameters; (ii) analytically derive an expression for the derivative of the forward model with respect to those parameters; (iii) use gradient-based optimization to solve an analysis-by-synthesis objective comparing measured and synthesized images. This approach has been used to recover shape [11,55,8], material [53,41,44], and illumination [39], either independently of each other or jointly [2,69,34,35,46].…”

Shadow Remover: Image Shadow Removal Based on Illumination Recovering Optimization

“…9, we give several shadow editing results by setting different values for η and ν. Compared with the shadow editing method [3] based on Poisson shadow interpolation and the illumination editing method [36], our method is easier to simulate a variety of lighting conditions. Our illumination recovering operator can also be applied to soften the sharp shadow edges, as illustrated in Fig.…”

Towards efficient image irradiance modelling of convex Lambertian surfaces under single viewpoint and frontal illumination

“…Note that the Lambertian kernel only depends on the radius of the hemisphere, which circumvents the Monge patch used to represent the object at hand, rather than the actual shape of the object. Hence, the Lambertian kernel in (19) fits into surfaces, which are homomorphic to a plane. In addition our near-light model {modified version of the model in [16]} assumes that the light source(s) lies on the locus of a hemisphere with radius greater than the object's size.…”

“…inverse lighting [17]} based on the appearance of objects aids applications such as augmented reality [18], where the inserted virtual objects are required to share the illumination conditions of the input image. According to previous works, it is common to assume the availability of a prior model of the viewed scene capturing its geometry and albedo [19]. We conduct illumination transfer experiments, where we recover illumination from an image E s of an object (referred to as ‘source’) and use the recovered lighting to render a different object E t (referred to as ‘target’).…”