M.Sc Student | Or-El Roy |
---|---|
Subject | Enhanced Active Vision |
Department | Department of Electrical Engineering | Supervisor | Professor Alfred Bruckstein |
Full Thesis text | ![]() |
The popularity of low-cost RGB-D scanners is increasing on a daily basis. Nevertheless, existing
scanners often cannot capture subtle details in the environment. We present a novel method to
enhance the depth map by fusing the intensity and depth information to create more detailed
range profiles. The proposed framework assumes that color and depth cues are taken from
a calibrated system, therefore they can be easily aligned. A normal map is estimated from a
smoothed version of the depth input. The acquired normal map together with the color image
and depth profile are then used to compute the scene lighting. The lighting model we use can
handle natural scene illumination. It recovers the shading of the image and then accounts for
albedos, shadows, and specularities. We then integrate the lighting model in a shape from
shading like technique to improve the visual fidelity of the reconstructed object. Unlike previous
efforts in this domain, the detailed geometry is calculated directly, without the need to explicitly
find and integrate surface normals. In addition, the proposed method operates four orders of
magnitude faster than the state of the art. Qualitative and quantitative visual and statistical
evidence support the improvement in the depth obtained by the suggested method.