Normal Map Bias Reduction for Many-Lights Multi-View Photometric Stereo

Abstract

In this paper, we improve upon an existing many-lights multi-view photometric stereo approach. Firstly, we show how to detect continuous regions for normal integration, which leads to a fully automatic reconstruction pipeline. Secondly, we compute perpixel light source visibilities using an initial biased reconstruction in order to update the estimated normal map to a solution with reduced bias. Thirdly, to further improve the normal accuracy, we compensate for interreflections of light between surface locations. Our approach is evaluated on both synthetic and real-world data and it is shown that the normal accuracy is improved by around 50 percent.