Intrinsic decomposition from a single spectral image

Abstract

In this paper, we present a spectral intrinsic image decomposition (SIID) model, which is dedicated to resolve a natural scene into its purely independent intrinsic components: illumination, shading, and reflectance. By introducing spectral information, our work can solve many challenging cases, such as scenes with metameric effects, which are hard to tackle for trichromatic intrinsic image decomposition (IID), and thus offers potential benefits to many higher-level vision tasks, e.g., materials classification and recognition, shape-from-shading, and spectral image relighting. A both effective and efficient algorithm is presented to decompose a spectral image into its independent intrinsic components. To facilitate future SIID research, we present a public dataset with ground-truth illumination, shading, reflectance and specularity, and a meaningful error metric, so that the quantitative comparison becomes achievable. The experiments on this dataset and other images demonstrate the accuracy and robustness of the proposed method on diverse scenes, and reveal that more spectral channels indeed facilitate the vision task (i.e., segmentation and recognition).

Multispectral Image Intrinsic Decomposition via Subspace Constraint

“…But it neglects the connection between pixels sharing the same neighborhood. On the basis of Retinex thoery, we follow work of Chen et al [12] to handle intrinsic image decomposition task in multispectral domain.…”

“…Material cues [26] has also been introduced. As to multispectral images, Chen et al [12] used super-pixel to cut down the number of unknown parameters in this underdetermined problem. Unlike the approaches above, we assumed that both shading and reflectance live in low dimensional subspace.…”

“…Bell et al [6] also introduced Intrinsic Images in the Wild, a large scale, public dataset for evaluating intrinsic image decompositions of indoor scenes. In multispectral field, [34,10] provided a set of multispectral images of various objects without ground truth, and Chen et al [12] built a dataset but the number, spectral resolution and diversity of images are limited. There is no other attempts to establish ground truth for multispectral intrinsic images.…”

“…We apply the updated mobile multispectral imaging camera to acquire the multispectral scenes, which could provide higher resolutions in spectral data ranging from 450nm-700nm with 118 spectral channels. Compared with the dataset provided by [12], ours is a similar but flowering in the diversity of projects with more detailed and bumpy scenarios which enables the dataset show further and potential applications in other vision researches (e.g. IRSS, segmentation and recognition).…”

“…It is clear that our method could produce pleasing visually decompositions based on multispectral images. In [12] generic constraint forces the sum value of a group of pixels to be a certain constant C, while in our method we let each pixel in shading image approximates to the pixel value of original image in the same position. Our generic constraint matrix is more sparse than that in [12], so that our algorithm will converge more quickly.…”