点击次数：

论文类型：期刊论文

发表时间：2021-01-10

发表刊物：IET IMAGE PROCESSING

卷号：14

期号：12

页面范围：2652-2659

ISSN号：1751-9659

关键字：image resolution; learning (artificial intelligence); iterative methods; image matching; stereo image processing; geometry; context guided refinement; existing end-to-end stereo matching networks; disparity matching phase; triangulation principle; domain differences; disparity refinement phase; refine; concatenated coarse disparity; fine disparity; unseen domain; stereo matching network; unseen scenes; context-guided refinement network; fine matching module; GCGR-Net learns; pixels; high

摘要：The disparity refinement phase of existing end-to-end stereo matching networks refines the disparity by learning the mapping from the concatenated coarse disparity and corresponding features to fine disparity. It depends on the scenarios' characteristics, such as the distribution of disparity and semantic categories contained in the domain, which makes the network fail to work on unseen domain. In this paper, we propose a geometry and context guided refinement network (GCGR-Net) containing a Fine Matching module and an Upsampling module. GCGR-Net learns to utilize pixels' relationship to get high resolution dense disparity, which is independent of the data's content. The Fine Matching module performs a minimum range search based on the relationship between the possible matching pixel pairs, i.e. the called geometry information, to recover the internal structure of the object. The Upsampling module obtains context information, the relationship between central pixel and the pixels in its neighborhood, to upsample the lower resolution disparity. The final disparity map is obtained step by step through an iterative refinement model. Experiment results show that our method not only has good performance in the training scenarios, but also outperforms previous methods on the unseen domain without fine-tuning.