CVMar 21, 2022

Global Matching with Overlapping Attention for Optical Flow Estimation

DeepMind
arXiv:2203.11335v1102 citationsh-index: 104Has Code
Originality Incremental advance
AI Analysis

This addresses the problem of handling large displacements in optical flow for computer vision applications, representing an incremental advancement over existing methods.

The paper tackles optical flow estimation by introducing a global matching step before direct regression to handle large motions, resulting in GMFlowNet outperforming RAFT and achieving state-of-the-art performance on benchmarks with major improvements in textureless regions and large motions.

Optical flow estimation is a fundamental task in computer vision. Recent direct-regression methods using deep neural networks achieve remarkable performance improvement. However, they do not explicitly capture long-term motion correspondences and thus cannot handle large motions effectively. In this paper, inspired by the traditional matching-optimization methods where matching is introduced to handle large displacements before energy-based optimizations, we introduce a simple but effective global matching step before the direct regression and develop a learning-based matching-optimization framework, namely GMFlowNet. In GMFlowNet, global matching is efficiently calculated by applying argmax on 4D cost volumes. Additionally, to improve the matching quality, we propose patch-based overlapping attention to extract large context features. Extensive experiments demonstrate that GMFlowNet outperforms RAFT, the most popular optimization-only method, by a large margin and achieves state-of-the-art performance on standard benchmarks. Thanks to the matching and overlapping attention, GMFlowNet obtains major improvements on the predictions for textureless regions and large motions. Our code is made publicly available at https://github.com/xiaofeng94/GMFlowNet

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes