Papers › Real-Time Video Super-Resolution with Spatio-Temporal Networks and Motion Compensation

Real-Time Video Super-Resolution with Spatio-Temporal Networks and Motion Compensation

16 Nov 2016CVPR 2017 7arXiv:1611.05250archive 2025-07-28

Jose Caballero, Christian Ledig, Andrew Aitken, Alejandro Acosta, Johannes Totz, Zehan Wang, Wenzhe Shi

Convolutional neural networks have enabled accurate image super-resolution in real-time. However, recent attempts to benefit from temporal correlations in video super-resolution have been limited to naive or inefficient architectures. In this paper, we introduce spatio-temporal sub-pixel convolution networks that effectively exploit temporal redundancies and improve reconstruction accuracy while maintaining real-time speed. Specifically, we discuss the use of early fusion, slow fusion and 3D convolutions for the joint processing of multiple consecutive video frames. We also propose a novel joint motion compensation and video super-resolution algorithm that is orders of magnitude more efficient than competing methods, relying on a fast multi-resolution spatial transformer module that is end-to-end trainable. These contributions provide both higher accuracy and temporally more consistent videos, which we confirm qualitatively and quantitatively. Relative to single-frame models, spatio-temporal networks can either reduce the computational cost by 30% whilst maintaining the same quality or provide a 0.2dB gain for a similar computational cost. Results on publicly available datasets demonstrate that the proposed algorithms surpass current state-of-the-art performance in both accuracy and efficiency.

PaperPDFConference PDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Motion CompensationVideo Super-Resolution

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Super-Resolution MSU Video Upscalers: Quality Enhancement VESPCN PSNR 26.92 #39 of 48 Archive leaderboard report
Video Super-Resolution MSU Video Upscalers: Quality Enhancement VESPCN SSIM 0.932 #39 of 48 Archive leaderboard report
Video Super-Resolution MSU Video Upscalers: Quality Enhancement VESPCN VMAF 53.96 #39 of 48 Archive leaderboard report
Video Super-Resolution Vid4 - 4x upscaling VESPCN MOVIE 5.82 #19 of 27 Archive leaderboard report
Video Super-Resolution Vid4 - 4x upscaling VESPCN PSNR 25.35 #19 of 27 Archive leaderboard report
Video Super-Resolution Vid4 - 4x upscaling VESPCN SSIM 0.7557 #19 of 27 Archive leaderboard report
Video Super-Resolution Vid4 - 4x upscaling bicubic MOVIE 9.31 #24 of 27 Archive leaderboard report
Video Super-Resolution Vid4 - 4x upscaling bicubic PSNR 23.82 #24 of 27 Archive leaderboard report
Video Super-Resolution Vid4 - 4x upscaling bicubic SSIM 0.6548 #24 of 27 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Convolution

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections