Abstract
Helmholtz Stereopsis is a powerful technique for reconstruction of scenes with arbitrary re ectance properties. However, previous formulations have been limited to static objects due to the requirement to se- quentially capture reciprocal image pairs (i.e. two im- ages with the camera and light source positions mu- tually interchanged). In this paper, we propose Colour Helmholtz Stereopsis - a novel framework for Helmholtz Stereopsis based on wavelength multiplexing. To ad- dress the new set of challenges introduced by multispec- tral data acquisition, the proposed Colour Helmholtz Stereopsis pipeline uniquely combines a tailored pho- tometric calibration for multiple camera/light source pairs, a novel procedure for spatio-temporal surface chromaticity calibration and a state-of-the-art Bayesian formulation necessary for accurate reconstruction from a minimal number of reciprocal pairs. In this frame- work, re ectance is spatially unconstrained both in terms of its chromaticity and the directional component dependent on the illumination incidence and viewing angles. The proposed approach for the rst time en- ables modelling of dynamic scenes with arbitrary un- known and spatially varying re ectance using a practi- cal acquisition set-up consisting of a small number of cameras and light sources. Experimental results demon- strate the accuracy and exibility of the technique on a variety of static and dynamic scenes with arbitrary un- known BRDF and chromaticity ranging from uniform to arbitrary and spatially varying.