BiFormer: Learning Bilateral Motion Estimation via Bilateral Transformer for 4K Video Frame Interpolation

TL;DR

This paper introduces BiFormer, a transformer-based bilateral motion estimator for 4K video frame interpolation, achieving high-quality results through global motion estimation, local refinement, and frame synthesis.

Contribution

It presents the first transformer-based bilateral motion estimator for 4K video interpolation, combining global and local motion refinement for improved accuracy.

Findings

Achieves state-of-the-art interpolation quality on 4K datasets.

Efficiently refines global motion fields using blockwise bilateral cost volumes.

Demonstrates superior performance compared to existing methods.

Abstract

A novel 4K video frame interpolator based on bilateral transformer (BiFormer) is proposed in this paper, which performs three steps: global motion estimation, local motion refinement, and frame synthesis. First, in global motion estimation, we predict symmetric bilateral motion fields at a coarse scale. To this end, we propose BiFormer, the first transformer-based bilateral motion estimator. Second, we refine the global motion fields efficiently using blockwise bilateral cost volumes (BBCVs). Third, we warp the input frames using the refined motion fields and blend them to synthesize an intermediate frame. Extensive experiments demonstrate that the proposed BiFormer algorithm achieves excellent interpolation performance on 4K datasets. The source codes are available at https://github.com/JunHeum/BiFormer.