원문정보
초록
영어
Recent development in virtual and augmented reality increases the demand for content in many different fields. One of the fast ways to create content for VR is 3D modeling of real objects. In this paper we propose a system to reconstruct three-dimensional models of real objects from the set of two-dimensional images under the assumption that the subject does not has distinct features. We explicitly consider an object that is made of one or more surfaces and radiant constant energy isotropically. We design a low cost portable multi camera rig system that is capable of capturing images simultaneously from all cameras. In order to evaluate the performance of the proposed system, comparison is made between 3D model and a CAD model. A simple algorithm is also proposed to acquire original texture or color of the subject. Using best pattern found after the experiments, 3D model of the Pyeongchang Olympic Mascot “Soohorang” is created to use as VR content
목차
1. Introduction
2. Related Work
3. Proposed System
4. Methodology
4.1 Feature detection using SIFT
4.2 SfM - Feature matching and Bundle Adjustment
4.3 Dense point cloud reconstruction
4.4 Mesh reconstruction
4.5 Mesh simplification
4.6 Texture replacement
5. Comparison and Evaluation
6. Result and Discussion
7. Making of VR Contents
8. Conclusion
Acknowledgement
References