由影像與輪廓建立三維體素模型

Voxel-based 3D Model Reconstruction from Images and Silhouettes

林大凱(Ta-Kai Lin)

指導教授 ： 莊永裕

國立臺灣大學/電機資訊學院/資訊網路與多媒體研究所/碩士(2015年)

https://doi.org/10.6342/NTU.2015.01636

摘要

本論文建立了一個用影像與輪廓資訊重建出三維模型的系統,而且所生成
的三維模型可以直接給三維印表機列印。我們對於使用手機拍攝的影像的特性
與所產生的問題做探討,並修改現有的系統使之可以健全地重建模型。
本論文採用 Volumetric Graph-cuts(體積圖形割) [3, 21, 20] 為基礎,實
現 Multi-View Stereo 的系統,輸出以體素(voxel)組成的模型。他是用一
個能量函數來描述這個系統的組成,然後建立一個馬可夫隨機場(Markov
Random Field),透過最小割(minimum cut)求得最佳解,即把模型空間中
所有體素分離成模型與背景。
由於所輸入的影像是由手機或消費型裝置拍攝,所以不可避免地影像會
有瑕疵。而現有的 Multi-View Stereo 做出來的結果不理想,最後的模型往往
會被雜訊影響到。所以,本論文研究了影像雜訊在計算過程的影響,提出了
(1) 計算前將影像縮圖,與 (2) 套用閾值過濾(Threshold Filter)於原本的算
法 [20] 來改善重建模型的品質。
所以,本論文的方法融合了來自影像的色彩線索,與來自輪廓的形狀限制,
集這兩個優點於一,設計出一個系統。而這個系統可以接受有雜訊的影像,重
建出一個完整的可列印的模型。

關鍵字

三維重建 ； 體素模型 ； 體積圖形割

並列摘要

In this thesis, we propose a 3d model reconstruction system from images
and silhouettes, and its output models are printable. We also studied char-
acteristics and problems of images shot with mobile phones, and altered an
existing method in order to reconstruct 3d model robustly.
We built a multi-view stereo system based on Volumetric Graph-cuts [3,
21, 20], which generates models composed of voxels. The structure of the
system is described by an energy function, and a Markov Random Field is
built to optimize. Finally, all the voxels in the space are divided into model
and background.
Because of images captured with model phones, noise and artifacts are
hardly avoided. However, existing multi-view stereo methods are not noise-
tolerant and thus produce bad models impacted by noise. Hence, this thesis
digged into the interference of noise, and came up with two solutions: (1)
Shrinking images before computation, and (2) Add threshold filter to the orig-
inal algorithm [20].
In conclusion, in the thesis we combined the photo clue from color images
and shape constraint from silhouettes into a system. The system not only
accepts noisy images but also produces printable models.

並列關鍵字

3D Reconstruction ； Voxel-based Model ； Volumetric Graph- cuts

參考文獻

[3] Y. Boykov and V. Kolmogorov. Computing geodesics and minimal surfaces via

14-17 October 2003, Nice, France, pages 26–33, 2003.

[4] Y. Boykov, O. Veksler, and R. Zabih. Fast approximate energy minimization via

graph cuts. IEEE Trans. Pattern Anal. Mach. Intell., 23(11):1222–1239, 2001.

segmentation from calibrated images. In Proceedings of the 2011 Conference for