paper-with-me

홈 › Papers

Sliding Window Recurrent Network for Efficient Video Super-Resolution

2022-08-24 · Wenyi Lian, Wenjing Lian

Video super-resolution (VSR) is the task of restoring high-resolution frames from a sequence of low-resolution inputs. Different from single image super-resolution, VSR can utilize frames' temporal information to reconstruct results with more details. Recently, with the rapid development of convolution neural networks (CNN), the VSR task has drawn increasing attention and many CNN-based methods have achieved remarkable results. However, only a few VSR approaches can be applied to real-world mobile devices due to the computational resources and runtime limitations. In this paper, we propose a \textit{Sliding Window based Recurrent Network} (SWRN) which can be real-time inference while still achieving superior performance. Specifically, we notice that video frames should have both spatial and temporal relations that can help to recover details, and the key point is how to extract and aggregate information. Address it, we input three neighboring frames and utilize a hidden state to recurrently store and update the important temporal information. Our experiment on REDS dataset shows that the proposed method can be well adapted to mobile devices and produce visually pleasant results.

📄 PDF Abstract BibTeX arXiv:2208.11608

Code (1)

shermanlian/swrn 공식 구현 tf

Tasks

Image Super-ResolutionSuper-ResolutionVideo Super-Resolution

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Video Super-Resolution with Recurrent Structure-Detail Network

2020-08-02 · ECCV 2020 8 · Takashi Isobe, Xu Jia, Shuhang Gu, Songjiang Li 외

Most video super-resolution methods super-resolve a single reference frame with the help of neighboring frames in a temporal sliding window. They are less efficient compared to the recurrent-based methods. In this work, …

Super-ResolutionVideo Super-Resolution

Stable Long-Term Recurrent Video Super-Resolution

2021-12-16 · CVPR 2022 1 · Benjamin Naoto Chiche, Arnaud Woiselle, Joana Frontera-Pons, Jean-Luc Starck

Recurrent models have gained popularity in deep learning (DL) based video super-resolution (VSR), due to their increased computational efficiency, temporal receptive field and temporal consistency compared to sliding-win…

Computational EfficiencySuper-ResolutionVideo Super-Resolution

Omniscient Video Super-Resolution

2021-03-29 · ICCV 2021 10 · Peng Yi, Zhongyuan Wang, Kui Jiang, Junjun Jiang 외

Most recent video super-resolution (SR) methods either adopt an iterative manner to deal with low-resolution (LR) frames from a temporally sliding window, or leverage the previously estimated SR output to help reconstruc…

Super-ResolutionVideo Super-Resolution

Frame-Recurrent Video Super-Resolution

2018-01-14 · CVPR 2018 6 · Mehdi S. M. Sajjadi, Raviteja Vemulapalli, Matthew Brown

Recent advances in video super-resolution have shown that convolutional neural networks combined with motion compensation are able to merge information from multiple low-resolution (LR) frames to generate high-quality im…

Motion CompensationMulti-Frame Super-ResolutionSuper-ResolutionVideo Super-Resolution

A Lightweight Recurrent Grouping Attention Network for Video Super-Resolution

2023-09-25 · Yonggui Zhu, Guofang Li

Effective aggregation of temporal information of consecutive frames is the core of achieving video super-resolution. Many scholars have utilized structures such as sliding windows and recurrent to gather spatio-temporal …

Super-ResolutionVideo Super-Resolution