MambaFlow: A Mamba-Centric Architecture for End-to-End Optical Flow Estimation

원문 초록

Recently, the Mamba architecture has demonstrated significant successes in various computer vision tasks, such as classification and segmentation. However, its application to optical flow estimation remains unexplored. In this paper, we introduce MambaFlow, a novel framework designed to leverage the high accuracy and efficiency of the Mamba architecture for capturing locally correlated features while preserving global information in end-to-end optical flow estimation. To our knowledge, MambaFlow is the first architecture centered around the Mamba design tailored specifically for optical flow estimation. It comprises two key components: (1) PolyMamba, which optimizes feature representation; and (2) PulseMamba, which facilitates efficient flow information dissemination. Our extensive experiments demonstrate that MambaFlow achieves remarkable results. On the Sintel benchmark, MambaFlow records an endpoint error (EPE) of 1.43 and an inference speed of 0.113 seconds, surpassing the state-of-the-art methods including GMFlow (with 18.9% lower EPE and 18.1% faster inference), SeparableFlow (5% lower EPE and 50.5% faster), CRAFT (1.11% lower EPE and 76.5% faster), and DIP (0.7% lower EPE and 77.2% faster)-demonstrating stronger potential for real-world deployment on resource-constrained devices. The source code will be made publicly available upon acceptance of the paper.