The paper proposes a technique for estimating outdoor illumination conditions in terms of sun and sky radiances directly from pixel values of dynamic shadows detected in video sequences produced by a commercial stereo camera. The technique is applied to the rendering of virtual objects into the image stream to achieve realistic Augmented Reality where the shading and shadowing of virtual objects is consistent with the real scene. Other techniques require the presence of a known object, a light probe, in the scene for estimating illumination. The technique proposed here works in general scenes and does not require High Dynamic Range imagery. Experiments demonstrate that sun and sky radiances are estimated to within 7% of ground truth values.
Abstract:The paper presents a technique for estimating the radiance of the sky and sun for outdoor, daylight illumination conditions. Shadows cast by dynamic objects are detected using color imagery, combined with depth information from a commercial stereo camera setup. Color information extracted from the detected shadows is used to estimate the radiance of the sun. The technique does not require special purpose objects in the scene, nor does it require High Dynamic Range imagery. Results are demonstrated by rendering augmented objects into real images with shading and shadows which are consistent with the real scene.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.