ATCA: an Arc Trajectory Based Model with Curvature Attention for Video Frame Interpolation
This work addresses a classic low-level computer vision task for video processing, offering a lightweight solution that improves efficiency and quality.
The authors tackled the problem of video frame interpolation by proposing an arc trajectory model that learns motion from only two frames, achieving better performance than many state-of-the-art methods with fewer parameters and faster inference speed.
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.