Abstract

This paper presents a marker-less method for full body hu- man performance capture by analyzing shading information from a se- quence of multi-view images, which are recorded under uncontrolled and changing lighting conditions. Both the articulated motion of the limbs and then the fine-scale surface detail are estimated in a temporally co- herent manner. In a temporal framework, differential 3D human pose- changes from the previous time-step are expressed in terms of constraints on the visible image displacements derived from shading cues, estimated albedo and estimated scene illumination. The incident illumination at each frame are estimated jointly with pose, by assuming the Lamber- tian model of reflectance. The proposed method is independent of image silhouettes and training data, and is thus applicable in cases where back- ground segmentation cannot be performed or a set of training poses is unavailable. We show results on challenging cases for pose-tracking such as changing backgrounds, occlusions and changing lighting conditions.