University of Oulu

Bengana, N., Mustaniemi, J., Heikkilä, J. (2022). Seeking Attention: Using Full Context Transformers for Better Disparity Estimation. In: El Yacoubi, M., Granger, E., Yuen, P.C., Pal, U., Vincent, N. (eds) Pattern Recognition and Artificial Intelligence. ICPRAI 2022. Lecture Notes in Computer Science, vol 13363. Springer, Cham.

Seeking attention : using full context transformers for better disparity estimation

Saved in:
Author: Bengana, Nadir1; Mustaniemi, Janne1; Heikkilä, Janne1
Organizations: 1University of Oulu, Oulu, Finland
Format: article
Version: accepted version
Access: embargoed
Persistent link:
Language: English
Published: Springer Nature, 2022
Publish Date: 2023-06-02


Until recently, convolutional neural networks have dominated various machine vision fields-including stereo disparity estimation-with little to no competition. Vision transformers have shaken up this domination with the introduction of multiple models achieving state of art results in fields such as semantic segmentation and object detection. In this paper, we explore the viability of stereo transformers, which are attention-based models inspired from NLP applications, by designing a transformer-based stereo disparity estimation as well as an end-to-end transformer architectures for both feature extraction and feature matching. Our solution is not limited by a pre-set maximum disparity and manages to achieve state of the art on SceneFlow dataset.

see all

Series: Lecture notes in computer science
ISSN: 0302-9743
ISSN-E: 1611-3349
ISSN-L: 0302-9743
ISBN: 978-3-031-09037-0
ISBN Print: 978-3-031-09036-3
Pages: 398 - 409
DOI: 10.1007/978-3-031-09037-0_33
Host publication: ICPRAI 2022: Pattern Recognition and Artificial Intelligence
Host publication editor: El Yacoubi, Mounîm
Granger, Eric
Yuen, Pong Chi
Pal, Umapada
Vincent, Nicole
Conference: International Conference on Pattern Recognition and Artificial Intelligence
Type of Publication: A4 Article in conference proceedings
Field of Science: 113 Computer and information sciences
Copyright information: © 2022 Springer Nature Switzerland AG.