Adaptive Neighbor Embedding for Efficient Stereo Matching
Aixin Chong, Hui Yin, Jin Wan, Yanting Liu, Qianqian Du · IEEE Transactions on Intelligent Vehicles · 2023
With the remarkable achievements of stereo matching algorithms based on Convolutional neural Networks (CNNs), more and more stereo matching algorithms based on CNNs are applied to intelligent driving research. Whereas, the existing convolution operators cannot fully mine and utilize the structure information, which is indispensable for stereo matching, especially in the regions with discontinuous disparity. In this work, to ameliorate these issues, an adaptive neighbor embedding paradigm (ANEparadigm) is proposed for deep stereo networks. In ourANEparadigm, the discriminative ability of features is improved by mining the neighbor correlation knowledge and performing adaptive neighbor aggregation. Specifically, we design a new convolution operator, termed adaptive neighbor embedding convolution (ANE conv) and its simplified version, termed adaptive neighbor embedding filter (ANE filter). BothANE convandANE filtercan be used as plug-and-play operators for all existing stereo matching models and can be easily trained end-to-end by standard back-propagation. Extensive experiments emphasize the performance of our approaches, especially in high accuracy metric.