Papers › Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with...

Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionary

16 Jan 2024CVPR 2024 1arXiv:2401.08209archive 2025-07-28

Leheng Zhang, Yawei Li, Xingyu Zhou, Xiaorui Zhao, Shuhang Gu

Single Image Super-Resolution is a classic computer vision problem that involves estimating high-resolution (HR) images from low-resolution (LR) ones. Although deep neural networks (DNNs), especially Transformers for super-resolution, have seen significant advancements in recent years, challenges still remain, particularly in limited receptive field caused by window-based self-attention. To address these issues, we introduce a group of auxiliary Adaptive Token Dictionary to SR Transformer and establish an ATD-SR method. The introduced token dictionary could learn prior information from training data and adapt the learned prior to specific testing image through an adaptive refinement step. The refinement strategy could not only provide global information to all input tokens but also group image tokens into categories. Based on category partitions, we further propose a category-based self-attention mechanism designed to leverage distant but similar tokens for enhancing input features. The experimental results show that our method achieves the best performance on various single image super-resolution benchmarks.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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="2401.08209")

Code

Syntology Ran 11 of 15 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 2 ran · our draft was wrong; 9 ran with no contract checked.

By repository: official repository: 15 samples from 1 repository, 11 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

labshuhanggu/adaptive-token-dictionary officialmentioned in papermentioned on GitHubpytorch 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

15 samples harvested; 11 ran; 0 honoured the contract we drafted; 4 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

2ran · our draft was wrong
9ran
4unverified

Licence: 0 of the 15 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 labshuhanggu/adaptive-token-dictionary. “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.

AC_MSA labshuhanggu/adaptive-token-dictionary/basicsr/archs/atd_arch.py official repository ran Apache-2.0 (permissive) · 2d93e34cbbe0fa7b · report
ATD_CA labshuhanggu/adaptive-token-dictionary/basicsr/archs/atd_arch.py official repository ran Apache-2.0 (permissive) · a705dbc0a3d310ee · report
ConvFFN_td labshuhanggu/adaptive-token-dictionary/basicsr/archs/atd_arch.py official repository ran Apache-2.0 (permissive) · ffc960c5105253ab · report
PatchEmbed labshuhanggu/adaptive-token-dictionary/basicsr/archs/atd_arch.py official repository ran Apache-2.0 (permissive) · 6317975e251ab4b3 · report
PatchUnEmbed labshuhanggu/adaptive-token-dictionary/basicsr/archs/atd_arch.py official repository ran Apache-2.0 (permissive) · 3732cc4a6f0ef56f · report
Upsample labshuhanggu/adaptive-token-dictionary/basicsr/archs/atd_arch.py official repository ran fingerprinted Apache-2.0 (permissive) · a3aba55c35e501fd · report
UpsampleOneStep labshuhanggu/adaptive-token-dictionary/basicsr/archs/atd_arch.py official repository ran Apache-2.0 (permissive) · 9f0f80f58d07551b · report
WindowAttention labshuhanggu/adaptive-token-dictionary/basicsr/archs/atd_arch.py official repository ran Apache-2.0 (permissive) · f6d717e16606d5e6 · report
dwconv labshuhanggu/adaptive-token-dictionary/basicsr/archs/atd_arch.py official repository ran Apache-2.0 (permissive) · 8962dc49cd030b9e · report
feature_shuffle labshuhanggu/adaptive-token-dictionary/basicsr/archs/atd_arch.py official repository ran · our draft was wrong Apache-2.0 (permissive) · 71f42c96ab0f7f91 · report
index_reverse labshuhanggu/adaptive-token-dictionary/basicsr/archs/atd_arch.py official repository ran · our draft was wrong Apache-2.0 (permissive) · 631a9cdc62e42ba1 · report
ATD labshuhanggu/adaptive-token-dictionary/basicsr/archs/atd_arch.py official repository unverified Apache-2.0 (permissive) · ea638ff98268e1f2 · report
ATDB labshuhanggu/adaptive-token-dictionary/basicsr/archs/atd_arch.py official repository unverified Apache-2.0 (permissive) · 7d7aefff486dc4f7 · report
ATDTransformerLayer labshuhanggu/adaptive-token-dictionary/basicsr/archs/atd_arch.py official repository unverified Apache-2.0 (permissive) · 3284755d16ba68ae · report
BasicBlock labshuhanggu/adaptive-token-dictionary/basicsr/archs/atd_arch.py official repository unverified Apache-2.0 (permissive) · 40f551c6bc695162 · report

Tasks

Image Super-ResolutionSuper-Resolution

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Super-Resolution Set14 ATD PSNR 29.24 #1 of 1 Archive leaderboard report
Image Super-Resolution Set14 - 4x upscaling ATD PSNR 29.24 #16 of 104 Archive leaderboard report
Image Super-Resolution Set14 - 4x upscaling ATD SSIM 0.7974 #16 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