從單張影像中估測多平面場景之光照環境

Lighting Estimation from a Single Image of Multiple Planes

郭炳成(Kuo, Ping Cheng)

指導教授 ： 賴尚宏

國立清華大學/電機資訊學院/資訊工程學系/碩士(2015年)

https://doi.org/10.6843/NTHU.2015.00361

摘要

在本篇論文中，我們提出一套針對在具有多平面的場景中可估測近點光源之演算法。藉由偵測平面標記，我們可以估測場景的三維空間配置。透過計算，我們可轉換影像像素從影像坐標系至世界坐標系以便於估測光源位置，最後輸出的光照參數可藉由最小化誤差函數得到。在實驗的部分，我們分別使用合成的影像以及現實的影像進行評估，在實驗中，我們使用合成的影像以及現實的數據集進行評估，並於實驗結果顯示出我們所提出的演算法優於目前較先進的光照估測方法。此外我們同時也發展擴增實境系統，在應用光照效果在繪製虛擬物件的部分，運用到本論文方法所估測出之光照參數，給予逼真的視覺效果。

關鍵字

電腦視覺 ； 光照估測 ； 擴增實境

並列摘要

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.

並列關鍵字

Computer vision ； Lighting estimation ； Augmented reality

參考文獻

[5] J. F. Blinn. Models of light reflection for computer synthesized pictures. In ACM SIGGRAPH Computer Graphics, volume 11, pages 192–198. ACM, 1977.

[8] M.W. Powell, S. Sarkar, and D. Goldgof. A simple strategy for calibrating the geometry of light sources. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 23(9):1022–1027, 2001.

[9] T. Takai, A. Maki, K. Niinuma, and T. Matsuyama. Difference sphere: an approach to near light source estimation. Computer Vision and Image Understanding, 113(9):966–978, 2009.

[10] K. Kato, F. Sakaue, and J. Sato. Extended multiple view geometry for lights and cameras from photometric and geometric constraints. In Pattern Recognition (ICPR), 2010 20th International Conference on, pages 2110–2113. IEEE, 2010.

[11] K.-Y. K. Wong, D. Schnieders, and S. Li. Recovering light directions and camera poses from a single sphere. In Computer Vision–ECCV 2008, pages 631–642. Springer, 2008.