UFM (Unified Flow & Matching, UniFlowMatch) is a simple, end-to-end trained transformer model that directly regresses pixel displacement images (flow) and can be applied concurrently to both optical ...
Abstract: Contemporary deep learning approaches for optical flow estimation continue to face persistent challenges in model interpretability, generalization capacity, and deployment efficiency, ...
Abstract: The sparse optical flow method is a fundamental task in computer vision. However, its reliance on the assumption of constant environmental brightness constrains its applicability in high ...