HMAFlow: Learning More Accurate Optical Flow via Hierarchical Motion Field Alignment
This work addresses a domain-specific problem in computer vision for improving optical flow accuracy in challenging scenes, representing an incremental advancement over existing methods.
The paper tackles optical flow estimation, particularly for small objects, by introducing HMAFlow with hierarchical motion field alignment and correlation self-attention modules, achieving relative error reductions of up to 14.2% on Sintel and 7.7% on KITTI benchmarks compared to state-of-the-art methods.
Optical flow estimation is a fundamental and long-standing visual task. In this work, we present a novel method, dubbed HMAFlow, to improve optical flow estimation in challenging scenes, particularly those involving small objects. The proposed model mainly consists of two core components: a Hierarchical Motion Field Alignment (HMA) module and a Correlation Self-Attention (CSA) module. In addition, we rebuild 4D cost volumes by employing a Multi-Scale Correlation Search (MCS) layer and replacing average pooling in common cost volumes with a search strategy utilizing multiple search ranges. Experimental results demonstrate that our model achieves the best generalization performance compared to other state-of-the-art methods. Specifically, compared with RAFT, our method achieves relative error reductions of 14.2% and 3.4% on the clean pass and final pass of the Sintel online benchmark, respectively. On the KITTI test benchmark, HMAFlow surpasses RAFT and GMA in the Fl-all metric by relative margins of 6.8% and 7.7%, respectively. To facilitate future research, our code will be made available at https://github.com/BooTurbo/HMAFlow.