M2Flow: A Motion Information Fusion Framework for Enhanced Unsupervised Optical Flow Estimation in Autonomous Driving
Abstract
Estimating optical flow in occluded regions is a crucial challenge in unsupervised settings. In this work, we introduce M2Flow, a novel framework for unsupervised optical flow estimation that integrates motion information from multiple frames to address occlusions. By modeling inter-frame motion information and employing Motion Information Propagation (MIP) module, M2Flow effectively propagates and integrates motion information across frames, while concurrently estimating bidirectional optical flows for multiple frames. In addition, to handle occlusions across multiple frames, we provide two augmentation modules specifically designed for our multi-frame model to further refine optical flow. The experiments on KITTI and Sintel datasets demonstrate that M2Flow outperforms other state-of-the-art unsupervised approaches, especially in solving occlusions.
Cite
Text
Sun et al. "M2Flow: A Motion Information Fusion Framework for Enhanced Unsupervised Optical Flow Estimation in Autonomous Driving." AAAI Conference on Artificial Intelligence, 2025. doi:10.1609/AAAI.V39I7.32767Markdown
[Sun et al. "M2Flow: A Motion Information Fusion Framework for Enhanced Unsupervised Optical Flow Estimation in Autonomous Driving." AAAI Conference on Artificial Intelligence, 2025.](https://mlanthology.org/aaai/2025/sun2025aaai-m/) doi:10.1609/AAAI.V39I7.32767BibTeX
@inproceedings{sun2025aaai-m,
title = {{M2Flow: A Motion Information Fusion Framework for Enhanced Unsupervised Optical Flow Estimation in Autonomous Driving}},
author = {Sun, Xunpei and Chen, Gang and Hou, Zuoxun},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2025},
pages = {7140-7148},
doi = {10.1609/AAAI.V39I7.32767},
url = {https://mlanthology.org/aaai/2025/sun2025aaai-m/}
}