Depth from a polarisation + RGB stereo pair

Abstract

In this paper, we propose a hybrid depth imaging system in which a polarisation camera is augmented by a second image from a standard digital camera. For this modest increase in equipment complexity over conventional shape-from-polarisation, we obtain a number of benefits that enable us to overcome longstanding problems with the polarisation shape cue. The stereo cue provides a depth map which, although coarse, is metrically accurate. This is used as a guide surface for disambiguation of the polarisation surface normal estimates using a higher order graphical model. In turn, these are used to estimate diffuse albedo. By extending a previous shape-from-polarisation method to the perspective case, we show how to compute dense, detailed maps of absolute depth, while retaining a linear formulation. We show that our hybrid method is able to recover dense 3D geometry that is superior to state-of-the-art shape-from-polarisation or two view stereo alone.

Publication
In IEEE Conference on Computer Vision and Pattern Recognition 2019
From a stereo pair of one polarisation image and one RGB image (a) we merge stereo depth with polarisation normals using a higher order graphical model (b) before estimating an albedo map and the final geometry (c).
Avatar
Dizhong Zhu
Computer Vision Engineer
Avatar
Will Smith
Professor in Computer Vision