,

Changlin Liu1, Linjun Sun2, Xin Ning2

  • 1Institute of Semiconductors, Chinese Academy of Sciences, Beijing, 100083, China; School of Semiconductor Science and Technology, South China Normal University, Foshan, 528225, China.

概括

本研究介绍了错误区域特征精细化机制 (EFR) 和双约束成本体积 (DCV) 以改善在具有挑战性的图像区域中的立体相匹配. 拟议的错误纠正功能引导立体声匹配网络 (ERCNet) 取得了最先进的结果.