Papers › RSTT: Real-time Spatial Temporal Transformer for Space-Time Video Super-Resolution

RSTT: Real-time Spatial Temporal Transformer for Space-Time Video Super-Resolution

27 Mar 2022CVPR 2022 1arXiv:2203.14186archive 2025-07-28

Zhicheng Geng, Luming Liang, Tianyu Ding, Ilya Zharkov

Space-time video super-resolution (STVSR) is the task of interpolating videos with both Low Frame Rate (LFR) and Low Resolution (LR) to produce High-Frame-Rate (HFR) and also High-Resolution (HR) counterparts. The existing methods based on Convolutional Neural Network (CNN) succeed in achieving visually satisfied results while suffer from slow inference speed due to their heavy architectures. We propose to resolve this issue by using a spatial-temporal transformer that naturally incorporates the spatial and temporal super resolution modules into a single model. Unlike CNN-based methods, we do not explicitly use separated building blocks for temporal interpolations and spatial super-resolutions; instead, we only use a single end-to-end transformer architecture. Specifically, a reusable dictionary is built by encoders based on the input LFR and LR frames, which is then utilized in the decoder part to synthesize the HFR and HR frames. Compared with the state-of-the-art TMNet, our network is 60% smaller (4.5M vs 12.3M parameters) and 80% faster (26.2fps vs 14.3fps on 720×576 frames) without sacrificing much performance. The source code is available at https://github.com/llmpass/RSTT.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 14 code samples harvested from 1 repository linked to this paper: 8 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 14 samples from 1 repository, 8 ran (5 with no instrument failure; 3 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

llmpass/RSTT officialmentioned in papermentioned on GitHubpytorchSyntology: 14 samples, 8 ran (3 instrument-failed) · 6 unverified 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

14 samples harvested: 8 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · our draft was wrong
2ran; the contract check could not run
5ran
6unverified

Licence: 14 of the 14 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 llmpass/RSTT. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

llmpass/RSTT official repository 14 samples, 8 ran (3 instrument-failed) · 6 unverified
Downsample in 58 papers models/RSTT.py ran no licence file found · pointer only · 190b1325503c4ab8 · report fixture: returned Downsample · level recorded 2026-09-22
InputProj models/RSTT.py ran no licence file found · pointer only · 3aee7fafe363d322 · report fixture: returned InputProj · level recorded 2026-09-22
ResidualBlock_noBN in 5 papers models/RSTT.py ran no licence file found · pointer only · b80f785c8fa3697e · report fixture: returned ResidualBlock_noBN · level recorded 2026-09-22
Upsample in 77 papers models/RSTT.py ran no licence file found · pointer only · 9d6b9fecff821851 · report fixture: returned Upsample · level recorded 2026-09-22
WindowAttention3D in 10 papers models/RSTT.py ran no licence file found · pointer only · 6f69c55b59c9744c · report fixture: returned WindowAttention3D · level recorded 2026-09-22
get_window_size in 21 papers models/RSTT.py ran; the contract check could not run (RAISES) no licence file found · pointer only · d306f10d62b6ae0c · report fixture: signature x_size:tuple/1/int, window_size:tuple/1/int, shift_size:tuple/1/int · returned tuple · level recorded 2026-09-22
window_partition in 377 papers
census: 13 implementations from 17 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
models/RSTT.py ran; the contract check could not run (RAISES) no licence file found · pointer only · dbf81aece2a63747 · report fixture: signature x:Tensor/5/float, window_size:tuple/1/int · returned Tensor · level recorded 2026-09-22
window_reverse in 296 papers models/RSTT.py ran · our draft was wrong no licence file found · pointer only · 15e141e09e3e5d8d · report fixture: signature windows:Tensor/5/float, window_size:tuple/1/int, B:int/0/int, D:int/0/int, H:int/0/int, W:int/0/int · returned Tensor · level recorded 2026-09-22
DecoderLayer in 43 papers models/RSTT.py unverified no licence file found · pointer only · cb3cd3a0e1663f15 · report
EncoderLayer in 73 papers models/RSTT.py unverified no licence file found · pointer only · 8e283aa9300b35c3 · report
RSTT models/RSTT.py unverified no licence file found · pointer only · 6c382b558756a30b · report
VSTSRDecoderTransformerBlock models/RSTT.py unverified no licence file found · pointer only · 5b1fddb874b78287 · report
VSTSREncoderTransformerBlock models/RSTT.py unverified no licence file found · pointer only · 2206f8156a0c0bc6 · report
initialize_weights in 30 papers models/RSTT.py unverified no licence file found · pointer only · e217d1b65eaca404 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for RSTT (graph method: RSTT). 16 bricks; individually on a fixture: 10 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified. The assembly has not been run end-to-end.

  1. RSTT entry · level 0 · unverified · 6c382b558756a30b
  2. DecoderLayer helper · level 0 · unverified · cb3cd3a0e1663f15
  3. Downsample model · level 1 · ran · 190b1325503c4ab8
  4. EncoderLayer helper · level 0 · unverified · 8e283aa9300b35c3
  5. InputProj model · level 1 · ran · 3aee7fafe363d322
  6. ResidualBlock_noBN helper · level 1 · ran · b80f785c8fa3697e
  7. Upsample model · level 1 · ran · 9d6b9fecff821851
  8. make_layer helper · level 1 · ran · our draft was wrong · c04a23de0531da4a
  9. VSTSRDecoderTransformerBlock model · level 0 · unverified · 5b1fddb874b78287
  10. get_window_size helper · level 1 · ran; the contract check could not run (RAISES) · d306f10d62b6ae0c
  11. window_partition helper · level 1 · ran; the contract check could not run (RAISES) · dbf81aece2a63747
  12. VSTSREncoderTransformerBlock model · level 0 · unverified · 2206f8156a0c0bc6
  13. initialize_weights helper · level 0 · unverified · e217d1b65eaca404
  14. Mlp model · level 1 · ran · a1715055832f71fd
  15. WindowAttention3D model · level 1 · ran · 6f69c55b59c9744c
  16. window_reverse helper · level 1 · ran · our draft was wrong · 15e141e09e3e5d8d

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2203.14186") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

DecoderSpace-time Video Super-resolutionSuper-ResolutionVideo Frame InterpolationVideo Super-Resolution

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Space-time Video Super-resolution Vimeo90K-Fast RSTT-L PSNR 36.80 #2 of 4 Archive leaderboard report
Space-time Video Super-resolution Vimeo90K-Fast RSTT-L SSIM 0.9403 #2 of 4 Archive leaderboard report
Space-time Video Super-resolution Vimeo90K-Fast RSTT-M PSNR 36.78 #3 of 4 Archive leaderboard report
Space-time Video Super-resolution Vimeo90K-Fast RSTT-M SSIM 0.9401 #3 of 4 Archive leaderboard report
Space-time Video Super-resolution Vimeo90K-Fast RSTT-S PSNR 36.58 #4 of 4 Archive leaderboard report
Space-time Video Super-resolution Vimeo90K-Fast RSTT-S SSIM 0.9381 #4 of 4 Archive leaderboard report
Space-time Video Super-resolution Vimeo90K-Medium RSTT-L PSNR 35.66 #2 of 4 Archive leaderboard report
Space-time Video Super-resolution Vimeo90K-Medium RSTT-L SSIM 0.9381 #2 of 4 Archive leaderboard report
Space-time Video Super-resolution Vimeo90K-Medium RSTT-M PSNR 35.62 #3 of 4 Archive leaderboard report
Space-time Video Super-resolution Vimeo90K-Medium RSTT-M SSIM 0.9377 #3 of 4 Archive leaderboard report
Space-time Video Super-resolution Vimeo90K-Medium RSTT-S PSNR 35.43 #4 of 4 Archive leaderboard report
Space-time Video Super-resolution Vimeo90K-Medium RSTT-S SSIM 0.9358 #4 of 4 Archive leaderboard report
Video Frame Interpolation Vid4 - 4x upscaling RSTT-L PSNR 26.43 #2 of 5 Archive leaderboard report
Video Frame Interpolation Vid4 - 4x upscaling RSTT-L Parameters 7670000 #2 of 5 Archive leaderboard report
Video Frame Interpolation Vid4 - 4x upscaling RSTT-L SSIM 0.7994 #2 of 5 Archive leaderboard report
Video Frame Interpolation Vid4 - 4x upscaling RSTT-M PSNR 26.37 #3 of 5 Archive leaderboard report
Video Frame Interpolation Vid4 - 4x upscaling RSTT-M Parameters 6080000 #3 of 5 Archive leaderboard report
Video Frame Interpolation Vid4 - 4x upscaling RSTT-M SSIM 0.7978 #3 of 5 Archive leaderboard report
Video Frame Interpolation Vid4 - 4x upscaling RSTT-S PSNR 26.29 #5 of 5 Archive leaderboard report
Video Frame Interpolation Vid4 - 4x upscaling RSTT-S Parameters 4490000 #5 of 5 Archive leaderboard report
Video Frame Interpolation Vid4 - 4x upscaling RSTT-S SSIM 0.7941 #5 of 5 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

AttentionDense ConnectionsLayer NormalizationLinear LayerMulti-Head AttentionResidual ConnectionSPEEDSoftmaxStochastic DepthSwin Transformer

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