CDFI: Compression-Driven Network Design for Frame Interpolation

TL;DR

This paper introduces CDFI, a compression-driven network design for frame interpolation that significantly reduces model size through pruning and multi-resolution techniques, achieving comparable or better performance than larger models.

Contribution

The paper presents a novel compression-driven framework for frame interpolation that combines pruning and multi-resolution modules, enabling efficient and high-quality interpolation with much smaller models.

Findings

10X compressed AdaCoF performs similarly to the original.

The compressed model with multi-resolution boosts visual consistency.

Achieves superior performance with only a quarter of the original size.

Abstract

DNN-based frame interpolation--that generates the intermediate frames given two consecutive frames--typically relies on heavy model architectures with a huge number of features, preventing them from being deployed on systems with limited resources, e.g., mobile devices. We propose a compression-driven network design for frame interpolation (CDFI), that leverages model pruning through sparsity-inducing optimization to significantly reduce the model size while achieving superior performance. Concretely, we first compress the recently proposed AdaCoF model and show that a 10X compressed AdaCoF performs similarly as its original counterpart; then we further improve this compressed model by introducing a multi-resolution warping module, which boosts visual consistencies with multi-level details. As a consequence, we achieve a significant performance gain with only a quarter in size compared with the original AdaCoF. Moreover, our model performs favorably against other state-of-the-arts in a broad range of datasets. Finally, the proposed compression-driven framework is generic and can be easily transferred to other DNN-based frame interpolation algorithm. Our source code is available at https://github.com/tding1/CDFI.