FlowDA: Unsupervised Domain Adaptive Framework for Optical Flow Estimation
This work addresses the problem of limited real-world optical flow data for researchers and practitioners in computer vision, offering an incremental improvement through domain adaptation.
The paper tackles the challenge of improving optical flow estimation in real-world scenarios by addressing the domain gap between virtual and real datasets, introducing FlowDA, an unsupervised domain adaptive framework that outperforms state-of-the-art methods by 21.6% to 30.9%.
Collecting real-world optical flow datasets is a formidable challenge due to the high cost of labeling. A shortage of datasets significantly constrains the real-world performance of optical flow models. Building virtual datasets that resemble real scenarios offers a potential solution for performance enhancement, yet a domain gap separates virtual and real datasets. This paper introduces FlowDA, an unsupervised domain adaptive (UDA) framework for optical flow estimation. FlowDA employs a UDA architecture based on mean-teacher and integrates concepts and techniques in unsupervised optical flow estimation. Furthermore, an Adaptive Curriculum Weighting (ACW) module based on curriculum learning is proposed to enhance the training effectiveness. Experimental outcomes demonstrate that our FlowDA outperforms state-of-the-art unsupervised optical flow estimation method SMURF by 21.6%, real optical flow dataset generation method MPI-Flow by 27.8%, and optical flow estimation adaptive method FlowSupervisor by 30.9%, offering novel insights for enhancing the performance of optical flow estimation in real-world scenarios. The code will be open-sourced after the publication of this paper.