Accurate and Efficient Stereo Matching via Attention Concatenation Volume
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2024-04 · 46 (4) · 2461-2474
DOI: 10.1109/tpami.2023.3335480 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024-04. Verfasst von Gangwei Xu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 122-mal zitiert (Crossref) und nennt 37 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Stereo matching is a fundamental building block for many vision and robotics applications. An informative and concise cost volume representation is vital for stereo matching of high accuracy and efficiency. In this article, we present a novel cost volume construction method, named attention concatenation volume (ACV), which generates attention weights from correlation clues to suppress redundant information and enhance matching-related information in the concatenation volume. The ACV can be seamlessly embedded into most stereo matching networks, the resulting networks can use a more lightweight aggregation network and meanwhile achieve higher accuracy. We further design a fast version of ACV to enable real-time performance, named Fast-ACV, which generates high likelihood disparity hypotheses and the corresponding attention weights from low-resolution correlation clues to significantly reduce computational and memory cost and meanwhile maintain a satisfactory accuracy. Furthermore, we design a highly accurate network ACVNet and a real-time network Fast-ACVNet based on our ACV and Fast-ACV respectively, which achieve state-of-the-art performance on several benchmarks.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Xu, G., Wang, Y., Cheng, J., Tang, J., & Yang, X. (2024). Accurate and Efficient Stereo Matching via Attention Concatenation Volume. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(4), 2461-2474. https://doi.org/10.1109/tpami.2023.3335480
Vancouver
Xu G, Wang Y, Cheng J, Tang J, Yang X. Accurate and Efficient Stereo Matching via Attention Concatenation Volume. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024;46(4):2461-2474. doi:10.1109/tpami.2023.3335480
BibTeX
@article{Xu2024,
author = {Xu, Gangwei and Wang, Yun and Cheng, Junda and Tang, Jinhui and Yang, Xin},
title = {Accurate and Efficient Stereo Matching via Attention Concatenation Volume},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2024},
volume = {46},
number = {4},
pages = {2461--2474},
doi = {10.1109/tpami.2023.3335480}
}
EUVIMED