Video Frame Interpolation via Local Lightweight Bidirectional Encoding with Channel Attention Cascade

Abstract

Deep Neural Networks based video frame interpolation, synthesizing in-between frames given two consecutive neighboring frames, typically depends on heavy model architectures, preventing them from being deployed on small terminals. When directly adopting the lightweight network architecture from these models, the synthesized frames may suffer from poor visual appearance. In this paper, a lightweight-driven video frame interpolation network (L <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> BEC <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> ) is proposed. Concretely, we first improve the visual appearance by introducing the bidirectional encoding structure with channel attention cascade to better characterize the motion information; then we further adopt the local network lightweight idea into the aforementioned structure to significantly eliminate its redundant parts of the model parameters. As a result, our L <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> BEC <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> performs favorably at the cost of only one third of the parameters compared with the state-of-the-art methods on public datasets. Our source code is available at https://github.com/Pumpkin123709/LBEC.git.