Paper
2 May 2024 SMART: stratified matching and recurrent transformer for optical flow estimation
Kin-Chung Chan, Kin-Man Lam
Author Affiliations +
Proceedings Volume 13164, International Workshop on Advanced Imaging Technology (IWAIT) 2024; 131642S (2024) https://doi.org/10.1117/12.3019407
Event: International Workshop on Advanced Imaging Technology (IWAIT) 2024, 2024, Langkawi, Malaysia
Abstract
The current optical flow estimation method GMFlow, which combines a hierarchical refinement strategy with iterative refinement, has achieved very good performance. However, it struggles to handle frames in complex scenes well, mainly because of unreliable coarse predictions. In this paper, we present a Transformer-based parallel refinement network to improve the accuracy of coarse predictions and allow fine predictions to be adjusted, based on the accurate coarse positional information. Our proposed structure, called SMART, maximizes the utilization of coarse-level rich-information features that are discarded after global matching in GMFlow. Additionally, the parallel structure allows the coarse-level prediction to be refined throughout the process and updated with information from both levels. Experimental results show that our model outperforms the baseline on two important datasets, namely FlyingChairs and FlyingThings3D.
(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.
Kin-Chung Chan and Kin-Man Lam "SMART: stratified matching and recurrent transformer for optical flow estimation", Proc. SPIE 13164, International Workshop on Advanced Imaging Technology (IWAIT) 2024, 131642S (2 May 2024); https://doi.org/10.1117/12.3019407
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Transformers

Optical flow

Education and training

Feature extraction

Object detection

Data modeling

Interpolation

RELATED CONTENT


Back to Top