Learning Optical Flow with Adaptive Graph Reasoning

TL;DR

This paper introduces AGFlow, a novel graph-based method that explicitly reasons over scene context to improve optical flow estimation, achieving state-of-the-art accuracy on Sintel datasets.

Contribution

The paper proposes a new adaptive graph reasoning framework that decouples scene context reasoning from matching, enhancing optical flow accuracy.

Findings

Achieves EPE of 1.43 pixels on Sintel clean pass.

Outperforms state-of-the-art methods by over 11%.

Demonstrates robustness and accuracy improvements.

Abstract

Estimating per-pixel motion between video frames, known as optical flow, is a long-standing problem in video understanding and analysis. Most contemporary optical flow techniques largely focus on addressing the cross-image matching with feature similarity, with few methods considering how to explicitly reason over the given scene for achieving a holistic motion understanding. In this work, taking a fresh perspective, we introduce a novel graph-based approach, called adaptive graph reasoning for optical flow (AGFlow), to emphasize the value of scene/context information in optical flow. Our key idea is to decouple the context reasoning from the matching procedure, and exploit scene information to effectively assist motion estimation by learning to reason over the adaptive graph. The proposed AGFlow can effectively exploit the context information and incorporate it within the matching procedure, producing more robust and accurate results. On both Sintel clean and final passes, our AGFlow achieves the best accuracy with EPE of 1.43 and 2.47 pixels, outperforming state-of-the-art approaches by 11.2% and 13.6%, respectively.