Computer Graphics Forum · 2012 · 134 citations · 25 references
ComputingComputer ScienceComputer VisionDigital ImagingMachine VisionObject RecognitionReflectance ModelingShading ModelsSurface ShadingTexture AnalysisImage Texture AnalysisIntrinsic Image DecompositionLinear System IdentificationReflectanceReflectance DecompositionReflectance ReconstructionShading
Abstract Decomposing an input image into its intrinsic shading and reflectance components is a long‐standing ill‐posed problem. We present a novel algorithm that requires no user strokes and works on a single image. Based on simple assumptions about its reflectance and luminance, we first find clusters of similar reflectance in the image, and build a linear system describing the connections and relations between them. Our assumptions are less restrictive than widely‐adopted Retinex‐based approaches, and can be further relaxed in conflicting situations. The resulting system is robust even in the presence of areas where our assumptions do not hold. We show a wide variety of results, including natural images, objects from the MIT dataset and texture images, along with several applications, proving the versatility of our method.
25
Edwin H. Land, John J. McCann · Journal of the Optical Society of America · 1971 · 4K citations
Medicine, Physiology, Vision Science +14
RECOVERING INTRINSIC SCENE CHARACTERISTICS FROM IMAGES
Harry G. Barrow, Jay M. Tenenbaum · Cancer Medicine · 1978 · 721 citations
A Variational Framework for Retinex
Ron Kimmel, Michael Elad, Doron Shaked et al. · International Journal of Computer Vision · 2003 · 696 citations