ATCA: an Arc Trajectory Based Model with Curvature Attention for Video Frame Interpolation

TL;DR

This paper introduces ATCA, a lightweight video frame interpolation model that learns curvilinear motion trajectories from just two frames, outperforming many state-of-the-art methods in quality and speed.

Contribution

ATCA is a novel arc trajectory based model that captures curvilinear motion from two frames, reducing computational complexity and improving interpolation performance.

Findings

Outperforms many SOTA methods in quality.

Uses fewer parameters and has faster inference.

Learns motion priors from only two frames.

Abstract

Video frame interpolation is a classic and challenging low-level computer vision task. Recently, deep learning based methods have achieved impressive results, and it has been proven that optical flow based methods can synthesize frames with higher quality. However, most flow-based methods assume a line trajectory with a constant velocity between two input frames. Only a little work enforces predictions with curvilinear trajectory, but this requires more than two frames as input to estimate the acceleration, which takes more time and memory to execute. To address this problem, we propose an arc trajectory based model (ATCA), which learns motion prior from only two consecutive frames and also is lightweight. Experiments show that our approach performs better than many SOTA methods with fewer parameters and faster inference speed.