Papers › Recursive Generalization Transformer for Image Super-Resolution

Recursive Generalization Transformer for Image Super-Resolution

11 Mar 2023arXiv:2303.06373archive 2025-07-28

Zheng Chen, Yulun Zhang, Jinjin Gu, Linghe Kong, Xiaokang Yang

Transformer architectures have exhibited remarkable performance in image super-resolution (SR). Since the quadratic computational complexity of the self-attention (SA) in Transformer, existing methods tend to adopt SA in a local region to reduce overheads. However, the local design restricts the global context exploitation, which is crucial for accurate image reconstruction. In this work, we propose the Recursive Generalization Transformer (RGT) for image SR, which can capture global spatial information and is suitable for high-resolution images. Specifically, we propose the recursive-generalization self-attention (RG-SA). It recursively aggregates input features into representative feature maps, and then utilizes cross-attention to extract global information. Meanwhile, the channel dimensions of attention matrices (query, key, and value) are further scaled to mitigate the redundancy in the channel domain. Furthermore, we combine the RG-SA with local self-attention to enhance the exploitation of the global context, and propose the hybrid adaptive integration (HAI) for module integration. The HAI allows the direct and effective fusion between features at different levels (local or global). Extensive experiments demonstrate that our RGT outperforms recent state-of-the-art methods quantitatively and qualitatively. Code and pre-trained models are available at https://github.com/zhengchen1999/RGT.

PaperPDFCodeCode Syntology ran

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 12 code samples harvested from 1 repository linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 10 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; 4 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 12 samples from 1 repository, 11 ran (1 with no instrument failure; 10 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 between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

zhengchen1999/rgt officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 12 samples, 11 ran (10 instrument-failed) · 1 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

12 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 10 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

6ran · our draft was wrong
4ran; the contract check could not run
1ran
1unverified

Licence: 5 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. For 5 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from zhengchen1999/rgt. “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.

zhengchen1999/rgt official repository 12 samples, 11 ran (10 instrument-failed) · 1 unverified
flow_warp in 48 papers basicsr/archs/arch_util.py ran · our draft was wrong Apache-2.0 (permissive) · ef9faf68f492a375 · report fixture: signature x:Tensor/4/float, flow:Tensor/4/float, interp_mode:str/0/str, padding_mode:str/0/str, align_corners:bool/0/bool · returned Tensor · level recorded 2026-09-22
get_position_from_periods in 59 papers basicsr/models/lr_scheduler.py ran; the contract check could not run (RAISES) fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · cd569444547de84f · report fixture: signature iteration:int/0/int, cumulative_period:list/1/int · returned int · level recorded 2026-09-24
img2windows in 15 papers basicsr/archs/rgt_arch.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant Apache-2.0 (permissive) · 15c613ecceb6aa71 · report fixture: signature img:Tensor/4/float, H_sp:int/0/int, W_sp:int/0/int · returned Tensor · level recorded 2026-09-22
insert_bn in 12 papers basicsr/archs/vgg_arch.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 5360d45b71ae2bb1 · report fixture: signature names:list/1/str · returned list · level recorded 2026-09-22
make_layer in 76 papers basicsr/archs/arch_util.py ran · our draft was wrong Apache-2.0 (permissive) · 96ad5dc9ca239aec · report fixture: signature basic_block:callable/0/?, num_basic_block:int/0/int, in_channels:int/0/int, out_channels:int/0/int · returned Sequential · level recorded 2026-09-22
master_only in 15 papers basicsr/utils/dist_util.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · f6b0e1eb5b7df3e3 · report fixture: signature func:callable/0/? · returned function · level recorded 2026-09-24
reduce_loss in 75 papers basicsr/losses/loss_util.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · a648a03a952822c0 · report fixture: signature loss:Tensor/2/float, reduction:str/0/str · returned Tensor · level recorded 2026-09-26
reorder_image in 18 papers basicsr/metrics/metric_util.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) here; the stored copy is pointer only · 95067518dc16b3e5 · report fixture: signature img:ndarray/3/int, input_order:str/0/str · returned ndarray · level recorded 2026-09-24
resize_flow in 28 papers basicsr/archs/arch_util.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 5a1d8458dc7077a6 · report fixture: signature flow:Tensor/4/float, size_type:str/0/str, sizes:list/1/float, interp_mode:str/0/str, align_corners:bool/0/bool · returned Tensor · level recorded 2026-09-24
weight_reduce_loss in 61 papers basicsr/losses/loss_util.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 1ba39317ea81871a · report fixture: signature loss:Tensor/2/float, weight:Tensor/2/float, reduction:str/0/str · returned Tensor · level recorded 2026-09-26
windows2img in 15 papers basicsr/archs/rgt_arch.py ran · our draft was wrong Apache-2.0 (permissive) · 8cb23a62748d3b1c · report fixture: signature img_splits_hw:Tensor/3/float, H_sp:int/0/int, W_sp:int/0/int, H:int/0/int, W:int/0/int · returned Tensor · level recorded 2026-09-22
weighted_loss in 53 papers basicsr/losses/loss_util.py unverified Apache-2.0 (permissive) · cf63f8afc13f62a7 · report

Tasks

Image ReconstructionImage Super-ResolutionSuper-Resolution

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Super-Resolution Manga109 - 4x upscaling RGT+ PSNR 32.68 #10 of 50 Archive leaderboard report
Image Super-Resolution Manga109 - 4x upscaling RGT+ SSIM 0.9303 #10 of 50 Archive leaderboard report
Image Super-Resolution Manga109 - 4x upscaling RGT PSNR 32.50 #14 of 50 Archive leaderboard report
Image Super-Resolution Manga109 - 4x upscaling RGT SSIM 0.9291 #14 of 50 Archive leaderboard report
Image Super-Resolution Set14 - 4x upscaling RGT+ PSNR 29.28 #14 of 104 Archive leaderboard report
Image Super-Resolution Set14 - 4x upscaling RGT+ SSIM 0.7979 #14 of 104 Archive leaderboard report
Image Super-Resolution Set14 - 4x upscaling RGT PSNR 29.23 #18 of 104 Archive leaderboard report
Image Super-Resolution Set14 - 4x upscaling RGT SSIM 0.7972 #18 of 104 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

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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