Papers › Reference-based Video Super-Resolution Using Multi-Camera Video Triplets

Reference-based Video Super-Resolution Using Multi-Camera Video Triplets

28 Mar 2022CVPR 2022 1arXiv:2203.14537archive 2025-07-28

Junyong Lee, Myeonghee Lee, Sunghyun Cho, Seungyong Lee

We propose the first reference-based video super-resolution (RefVSR) approach that utilizes reference videos for high-fidelity results. We focus on RefVSR in a triple-camera setting, where we aim at super-resolving a low-resolution ultra-wide video utilizing wide-angle and telephoto videos. We introduce the first RefVSR network that recurrently aligns and propagates temporal reference features fused with features extracted from low-resolution frames. To facilitate the fusion and propagation of temporal reference features, we propose a propagative temporal fusion module. For learning and evaluation of our network, we present the first RefVSR dataset consisting of triplets of ultra-wide, wide-angle, and telephoto videos concurrently taken from triple cameras of a smartphone. We also propose a two-stage training strategy fully utilizing video triplets in the proposed dataset for real-world 4x video super-resolution. We extensively evaluate our method, and the result shows the state-of-the-art performance in 4x super-resolution.

PaperPDFConference PDFCode

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

Code

codeslake/RefVSR officialmentioned in papermentioned on GitHubpytorchAGPL-3.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

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

Tasks

Reference-based Video Super-ResolutionSuper-ResolutionVideo Super-Resolution

Datasets

Introduced by this paper, per the archive.

RealMCVSR

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Reference-based Video Super-Resolution RealMCVSR RefVSR-IR-ℓ1 PSNR 34.86 #1 of 10 Archive leaderboard report
Reference-based Video Super-Resolution RealMCVSR RefVSR-ℓ1 PSNR 34.74 #2 of 10 Archive leaderboard report
Reference-based Video Super-Resolution RealMCVSR RefVSR-small-ℓ1 PSNR 33.88 #3 of 10 Archive leaderboard report
Reference-based Video Super-Resolution RealMCVSR IconVSR-ℓch [chan2021basicvsr] PSNR 33.80 #4 of 10 Archive leaderboard report
Reference-based Video Super-Resolution RealMCVSR BasicVSR-ℓch [chan2021basicvsr] PSNR 33.66 #5 of 10 Archive leaderboard report
Reference-based Video Super-Resolution RealMCVSR EDVR-ℓch [wang2019edvr] PSNR 33.47 #6 of 10 Archive leaderboard report
Reference-based Video Super-Resolution RealMCVSR EDVR-M-ℓch [wang2019edvr] PSNR 33.26 #7 of 10 Archive leaderboard report
Reference-based Video Super-Resolution RealMCVSR DCSR-ℓ1 [wang2021DCSR] PSNR 32.43 #8 of 10 Archive leaderboard report
Reference-based Video Super-Resolution RealMCVSR RCAN-ℓ1 [zhang2018rcan] PSNR 31.07 #9 of 10 Archive leaderboard report
Reference-based Video Super-Resolution RealMCVSR TTSR-ℓ1 [yang2020TTSR] PSNR 30.83 #10 of 10 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.

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