PRAFlow_RVC: Pyramid Recurrent All-Pairs Field Transforms for Optical Flow Estimation in Robust Vision Challenge 2020

TL;DR

PRAFlow_RVC introduces a pyramid network structure building on RAFT for improved optical flow estimation, achieving high accuracy and robustness, and securing second place in ECCV 2020's Robust Vision Challenge.

Contribution

It proposes a pyramid recurrent network with two layers based on RAFT to enhance optical flow estimation robustness and accuracy.

Findings

Achieved second place in ECCV 2020 Robust Vision Challenge.

Built on RAFT with a pyramid structure for better performance.

Trained on diverse datasets demonstrating strong generalization.

Abstract

Optical flow estimation is an important computer vision task, which aims at estimating the dense correspondences between two frames. RAFT (Recurrent All Pairs Field Transforms) currently represents the state-of-the-art in optical flow estimation. It has excellent generalization ability and has obtained outstanding results across several benchmarks. To further improve the robustness and achieve accurate optical flow estimation, we present PRAFlow (Pyramid Recurrent All-Pairs Flow), which builds upon the pyramid network structure. Due to computational limitation, our proposed network structure only uses two pyramid layers. At each layer, the RAFT unit is used to estimate the optical flow at the current resolution. Our model was trained on several simulate and real-image datasets, submitted to multiple leaderboards using the same model and parameters, and won the 2nd place in the optical flow task of ECCV 2020 workshop: Robust Vision Challenge.