| 引用本文: | 吴琼玉,周东翔,刘云辉,等.一种视差域基于学习方法的图像合成算法.[J].国防科技大学学报,2007,29(6):39-43.[点击复制] |
| WU Qiongyu,ZHOU Dongxiang,LIU Yunhui,et al.View Synthesis Based on Learning in Disparity Field[J].Journal of National University of Defense Technology,2007,29(6):39-43[点击复制] |
|
| |
|
|
| 本文已被：浏览 6828次 下载 5659次 |
| 一种视差域基于学习方法的图像合成算法 |
| 吴琼玉, 周东翔, 刘云辉, 蔡宣平 |
|
(国防科技大学 电子科学与工程学院，湖南 长沙 410073)
|
| 摘要: |
| 基于图像序列的图像合成往往需要定标和恢复场景三维结构，为了避免这些复杂过程，根据参考图像的视点离虚拟视点的远近关系，将参考图像序列分为主、从参考图像，并利用多极约束的原理和非线性校正，将图像合成的最优化问题从深度域转化到视差域，从而在不定标和不匹配的情况下，直接从图像序列合成虚拟视图。实验结果证明算法是有效的，并有一定的应用前景。 |
| 关键词: 弱定标 校正 图像合成 |
| DOI： |
| 投稿日期：2007-03-28 |
| 基金项目:国家自然科学基金资助项目(60334010；60475029) |
|
| View Synthesis Based on Learning in Disparity Field |
| WU Qiongyu, ZHOU Dongxiang, LIU Yunhui, CAI Xuanping |
|
(College of Electronic Science and Engineering, National Univ. of Defense Technology, Changsha 410073，China)
|
| Abstract: |
| The process of calibration and 3D reconstruction of the scene are always required in view synthesis from image sequences. To avoid those complicated processes, the reference images are first classified into primary reference image and subordinate reference image according to the distance between the reference viewpoints and the novel viewpoint. Then the global optimization problem of view synthesis is transformed from the depth field to disparity field, using a process of nonlinear rectification and multi-epipolar technology. Finally, the novel view is synthesized from the image sequence without matching and calibration. Experimental results show that the method is effective and has potential in the future. |
| Keywords: weak calibration rectification view synthesis |
|
|
|
|
|
