EUVIMEDEUVIMED entdecken
Crossref

Recurrent Partial Kernel Network for Efficient Optical Flow Estimation

Henrique Morimitsu, Xiaobin Zhu, Xiangyang Ji, Xu-Cheng Yin

Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (5) · 4278-4286

DOI: 10.1609/aaai.v38i5.28224 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Henrique Morimitsu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 25-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Optical flow estimation is a challenging task consisting of predicting per-pixel motion vectors between images. Recent methods have employed larger and more complex models to improve the estimation accuracy. However, this impacts the widespread adoption of optical flow methods and makes it harder to train more general models since the optical flow data is hard to obtain. This paper proposes a small and efficient model for optical flow estimation. We design a new spatial recurrent encoder that extracts discriminative features at a significantly reduced size. Unlike standard recurrent units, we utilize Partial Kernel Convolution (PKConv) layers to produce variable multi-scale features with a single shared block. We also design efficient Separable Large Kernels (SLK) to capture large context information with low computational cost. Experiments on public benchmarks show that we achieve state-of-the-art generalization performance while requiring significantly fewer parameters and memory than competing methods. Our model ranks first in the Spring benchmark without finetuning, improving the results by over 10% while requiring an order of magnitude fewer FLOPs and over four times less memory than the following published method without finetuning. The code is available at github.com/hmorimitsu/ptlflow/tree/main/ptlflow/models/rpknet.

Zitieren

APA

Morimitsu, H., Zhu, X., Ji, X., & Yin, X. (2024). Recurrent Partial Kernel Network for Efficient Optical Flow Estimation. Proceedings of the AAAI Conference on Artificial Intelligence, 38(5), 4278-4286. https://doi.org/10.1609/aaai.v38i5.28224

Vancouver

Morimitsu H, Zhu X, Ji X, Yin X. Recurrent Partial Kernel Network for Efficient Optical Flow Estimation. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(5):4278-4286. doi:10.1609/aaai.v38i5.28224

BibTeX
@article{Morimitsu2024,
  author = {Morimitsu, Henrique and Zhu, Xiaobin and Ji, Xiangyang and Yin, Xu-Cheng},
  title = {Recurrent Partial Kernel Network for Efficient Optical Flow Estimation},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2024},
  volume = {38},
  number = {5},
  pages = {4278--4286},
  doi = {10.1609/aaai.v38i5.28224}
}
Kostenlos starten →