HMAFlow: Learning More Accurate Optical Flow via Hierarchical Motion Field Alignment
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.
Code (1)
Tasks
Optical Flow EstimationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Hierarchical Graph Pattern Understanding for Zero-Shot VOS
The optical flow guidance strategy is ideal for obtaining motion information of objects in the video. It is widely utilized in video segmentation tasks. However, existing optical flow-based methods have a significant dep…
DecoderGraph Neural NetworkOptical Flow EstimationSemantic Segmentation+4Unsupervised Hierarchical Domain Adaptation for Adverse Weather Optical Flow
Optical flow estimation has made great progress, but usually suffers from degradation under adverse weather. Although semi/full-supervised methods have made good attempts, the domain shift between the synthetic and real …
Domain AdaptationOptical Flow EstimationDeformable Non-local Network for Video Super-Resolution
The video super-resolution (VSR) task aims to restore a high-resolution (HR) video frame by using its corresponding low-resolution (LR) frame and multiple neighboring frames. At present, many deep learning-based VSR meth…
Optical Flow EstimationSuper-ResolutionVideo Super-ResolutionSensor-Guided Optical Flow
This paper proposes a framework to guide an optical flow network with external cues to achieve superior accuracy either on known or unseen domains. Given the availability of sparse yet accurate optical flow hints from an…
Optical Flow EstimationEfficient Coarse-To-Fine PatchMatch for Large Displacement Optical Flow
As a key component in many computer vision systems, optical flow estimation, especially with large displacements, remains an open problem. In this paper we present a simple but powerful matching method works in a coarse-…
Optical Flow Estimation