Unsupervised Flow Refinement near Motion Boundaries
This work addresses a specific challenge in unsupervised optical flow estimation for computer vision applications, but it is incremental as it builds on existing predictors.
The paper tackled the problem of poor optical flow estimates near motion boundaries in unsupervised deep learning methods by proposing a framework that detects boundaries and refines flow, achieving more accurate boundary detection than a baseline without additional training.
Unsupervised optical flow estimators based on deep learning have attracted increasing attention due to the cost and difficulty of annotating for ground truth. Although performance measured by average End-Point Error (EPE) has improved over the years, flow estimates are still poorer along motion boundaries (MBs), where the flow is not smooth, as is typically assumed, and where features computed by neural networks are contaminated by multiple motions. To improve flow in the unsupervised settings, we design a framework that detects MBs by analyzing visual changes along boundary candidates and replaces motions close to detections with motions farther away. Our proposed algorithm detects boundaries more accurately than a baseline method with the same inputs and can improve estimates from any flow predictor without additional training.