Lighting Estimation from a Single Image of Multiple Planes

• Main Authors: Kuo, Ping Cheng, 郭炳成
• Other Authors: Lai, Shang Hong
• Format: Others
• Language: zh-TW
• Published: 2015
• Online Access: http://ndltd.ncl.edu.tw/handle/18349403932974392171

碩士 === 國立清華大學 === 資訊工程學系 === 103 === In this thesis, we present a novel lighting estimation algorithm for the scene containing two or more planes. This thesis focuses on near point light source estimation. We detect planar markers to estimate the poses of the 3D planes in the scene. Then we transform the image pixels from image coordinates to world coordinates for the estimation of light position. The output of the proposed method is the lighting parameters estimated from minimizing the error function. In the experiments, we test on synthetic data and real dataset. Our experimental results show the proposed algorithm outperforms the state-of-the-art lighting estimation method. Moreover, we develop an augmented reality system that includes lighting estimation by using the proposed algorithm.