Year: 2023
Type: conference-paper
Abstract: Video frame interpolation (VFI) achieves temporal super-resolution by synthesizing intermediate frame between two original adjacent frames. This paper proposes a lightweight VFI network based on lightweight convolutional unit and three-scale encoder. We first introduce a three-scale encoding-decoding structure with two-level attention cascades to represent the multi-scale motion information. Then, recurrent convolutional layer (RCL) and residual operation are adopted to design the recurrent residual convolutional unit (RRCU) to refine the three-scale structure. Finally, we propose a lightweight unit by combining the depth separable convolution and RRCU, and introduce the local lightweight idea to reduce the model parameters. Experimental results show that the proposed method achieves a better performance against the state-of-the-art methods with fewer parameters.
Institution: University of Jinan
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
Awards: G2364123793, G4211522084
OpenAlex ID: W4387954906