Papers › Recurrent Back-Projection Network for Video Super-Resolution

Recurrent Back-Projection Network for Video Super-Resolution

25 Mar 2019CVPR 2019 6arXiv:1903.10128archive 2025-07-28

Muhammad Haris, Greg Shakhnarovich, Norimichi Ukita

We proposed a novel architecture for the problem of video super-resolution. We integrate spatial and temporal contexts from continuous video frames using a recurrent encoder-decoder module, that fuses multi-frame information with the more traditional, single frame super-resolution path for the target frame. In contrast to most prior work where frames are pooled together by stacking or warping, our model, the Recurrent Back-Projection Network (RBPN) treats each context frame as a separate source of information. These sources are combined in an iterative refinement framework inspired by the idea of back-projection in multiple-image super-resolution. This is aided by explicitly representing estimated inter-frame motion with respect to the target, rather than explicitly aligning frames. We propose a new video super-resolution benchmark, allowing evaluation at a larger scale and considering videos in different motion regimes. Experimental results demonstrate that our RBPN is superior to existing methods on several datasets.

PaperPDFConference PDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1903.10128")

Code

Syntology Ran 0 of 7 code samples harvested from 2 repositories linked to this paper; 7 have no recorded run.

By repository: community (archive-listed): 7 samples from 2 repositories, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

zhangtianmingxp/rbpn_mindspore mentioned on GitHubmindsporeApache-2.0 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

7 samples harvested; 0 ran; 0 honoured the contract we drafted; 7 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

7unverified

Licence: 0 of the 7 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

PSNR zhangtianmingxp/rbpn_mindspore/src/util/utils.py community (archive-listed) unverified Apache-2.0 (permissive) · b70f51832e08d34b · report
is_image_file alterzero/RBPN-PyTorch/dataset.py community (archive-listed) unverified MIT (permissive) · 0516d5020cce56da · report
is_image_file zhangtianmingxp/rbpn_mindspore/src/datasets/dataset.py community (archive-listed) unverified Apache-2.0 (permissive) · a20de656266e3549 · report
load_img alterzero/RBPN-PyTorch/dataset.py community (archive-listed) unverified MIT (permissive) · 459b69cbc957642b · report
load_img zhangtianmingxp/rbpn_mindspore/src/datasets/dataset.py community (archive-listed) unverified Apache-2.0 (permissive) · dfc5a69cdc89254e · report
load_img_future alterzero/RBPN-PyTorch/dataset.py community (archive-listed) unverified MIT (permissive) · b3920a12cdc50c5f · report
load_img_future zhangtianmingxp/rbpn_mindspore/src/datasets/dataset.py community (archive-listed) unverified Apache-2.0 (permissive) · 5fa00c1ba29fbcb7 · report

Tasks

DecoderImage Super-ResolutionSuper-ResolutionVideo Super-Resolution

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Super-Resolution MSU Super-Resolution for Video Compression RBPN + x264 BSQ-rate over ERQA 1.599 #25 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression RBPN + x264 BSQ-rate over LPIPS 1.335 #25 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression RBPN + x264 BSQ-rate over MS-SSIM 0.729 #25 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression RBPN + x264 BSQ-rate over PSNR 1.127 #25 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression RBPN + x264 BSQ-rate over Subjective Score 1.498 #25 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression RBPN + x264 BSQ-rate over VMAF 0.733 #25 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression RBPN + x265 BSQ-rate over ERQA 13.185 #32 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression RBPN + x265 BSQ-rate over LPIPS 13.237 #32 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression RBPN + x265 BSQ-rate over MS-SSIM 1.438 #32 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression RBPN + x265 BSQ-rate over PSNR 1.89 #32 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression RBPN + x265 BSQ-rate over Subjective Score 2.282 #32 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression RBPN + x265 BSQ-rate over VMAF 1.324 #32 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression RBPN + aomenc BSQ-rate over ERQA 13.572 #37 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression RBPN + aomenc BSQ-rate over LPIPS 5.821 #37 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression RBPN + aomenc BSQ-rate over MS-SSIM 3.089 #37 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression RBPN + aomenc BSQ-rate over PSNR 10.89 #37 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression RBPN + aomenc BSQ-rate over Subjective Score 2.7 #37 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression RBPN + aomenc BSQ-rate over VMAF 1.996 #37 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression RBPN + vvenc BSQ-rate over ERQA 18.314 #38 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression RBPN + vvenc BSQ-rate over LPIPS 11.777 #38 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression RBPN + vvenc BSQ-rate over MS-SSIM 0.884 #38 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression RBPN + vvenc BSQ-rate over PSNR 5.783 #38 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression RBPN + vvenc BSQ-rate over Subjective Score 2.719 #38 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression RBPN + vvenc BSQ-rate over VMAF 0.689 #38 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression RBPN + uavs3e BSQ-rate over ERQA 7.133 #43 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression RBPN + uavs3e BSQ-rate over LPIPS 4.859 #43 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression RBPN + uavs3e BSQ-rate over MS-SSIM 2.263 #43 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression RBPN + uavs3e BSQ-rate over PSNR 6.301 #43 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression RBPN + uavs3e BSQ-rate over Subjective Score 2.944 #43 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression RBPN + uavs3e BSQ-rate over VMAF 0.702 #43 of 85 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration RBPN 1 - LPIPS 0.74 #3 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration RBPN ERQAv1.0 0.746 #3 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration RBPN FPS 0.043 #3 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration RBPN PSNR 31.407 #3 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration RBPN QRCRv1.0 0.629 #3 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration RBPN SSIM 0.899 #3 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration RBPN Subjective score 7.068 #3 of 32 Archive leaderboard report
Video Super-Resolution Vid4 - 4x upscaling RBPN/6-PF PSNR 27.12 #15 of 27 Archive leaderboard report
Video Super-Resolution Vid4 - 4x upscaling RBPN/6-PF SSIM 0.8180 #15 of 27 Archive leaderboard report
Video Super-Resolution Vid4 - 4x upscaling - BD degradation RBPN PSNR 27.17 #15 of 18 Archive leaderboard report
Video Super-Resolution Vid4 - 4x upscaling - BD degradation RBPN SSIM 0.8205 #15 of 18 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

Introduced by this paper: RBPN

RBPN

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