A Practical Approach for Super-Resolution using Photometric Stereo and Graph Cuts

In this paper, we propose an approach to obtain super-resolved image and super-resolved depth map using photometric cue. The images are captured using different light source positions which are assumed to be known. The surface of the object is assumed to be Lambertian. We model the high resolution structure (surface gradients) as a Markov Random Field (MRF) and use graph cuts with discontinuity preservation to get a high resolution depth map. We then reconstruct the high resolution intensity map for each light source position using the high resolution surface gradients. Results of experimentation on synthetic and real data are presented. The advantage of the proposed approach is that its time complexity is much less as compared to the super-resolution approaches that use global optimization techniques such as simulated annealing. Also, since we are using photometric cue, there is no need of registration as is required in motion based approaches.