Skip to content

Opening book details…

Can I read EAI-Stereo: Error Aware Iterative Network for Stereo Matching on EtoBox?

EAI-Stereo: Error Aware Iterative Network for Stereo Matching by Haoliang Zhao; Huizhou Zhou; Yongjun Zhang; Yong Zhao; Yitong Yang; Ting Ouyang is a book available to read on EtoBox.

What is EAI-Stereo: Error Aware Iterative Network for Stereo Matching about?

Current state-of-the-art stereo algorithms use a 2D CNN to extract features and then form a cost volume, which is fed into the following cost aggregation and regularization module composed of 2D or 3D CNNs. However, a large amount of high-frequency information like texture, color variation, sharp edge etc. is not well exploited during this process, which leads to relatively blurry and lacking detailed disparity maps. In this paper, we aim at making full use of the high-frequency information from the original image. Towards this end, we propose an error-aware refinement module that incorporates high-frequency information from the original left image and allows the network to learn error correction capabilities that can produce excellent subtle details and sharp edges. In order to improve the data transfer efficiency between our iterations, we propose the Iterative Multiscale Wide-LSTM Network which could carry more semantic information across iterations. We demonstrate the efficiency and effectiveness of our method on KITTI 2015, Middlebury, and ETH3D. At the time of writing this paper, EAI-Stereo ranks 1 st on the Middlebury leaderboard and 1 st on the ETH3D Stereo benchmark for 50

Author
Haoliang Zhao; Huizhou Zhou; Yongjun Zhang; Yong Zhao; Yitong Yang; Ting Ouyang
Publisher
Springer Nature Switzerland : Imprint: Springer
Published
2023
Language
EN
ISBN
9783031263194
Subjects
Management, Computer Science, Engineering

More by Haoliang Zhao; Huizhou Zhou; Yongjun Zhang; Yong Zhao; Yitong Yang; Ting Ouyang

Browse all works by Haoliang Zhao; Huizhou Zhou; Yongjun Zhang; Yong Zhao; Yitong Yang; Ting Ouyang

Similar books