标题：Cost Aggregation Strategy for Stereo Matching Based on a Generalized Bilateral Filter Model
作者：Li, Li; Zhang, Cai-Ming; Yan, Hua
作者机构：[Li, Li; Zhang, Cai-Ming] Shandong Univ, Dept Comp Sci & Technol, Jinan 250100, Peoples R China.; [Li, Li; Zhang, Cai-Ming; Yan, Hua] Shandong Econ 更多
会议名称：International Conference on Information Computing and Applications
会议日期：OCT 15-18, 2010
来源：INFORMATION COMPUTING AND APPLICATIONS, PT 1
摘要：Stereo matching is a kernel problem in the field of stereo vision. An adaptive cost aggregation strategy based on a generalized bilateral filter model is proposed. The strategy extends range weights of the original bilateral filter by the inner and outer weighted average processes. A pixel is assigned a high range weight to the central pixel not only if the patches of the two pixels are similar but also if the neighboring patches around the two pixels are similar. The final range weights could more accurately reflect the similarities of relevant two pixels. Different; cost aggregation methods can be derived from the model by modifying parameters. Experimental results compared with the other state-of-the-art cost aggregation methods demonstrate the effectiveness of our proposed cost aggregation strategy.