Papers › CascadedGaze: Efficiency in Global Context Extraction for Image Restoration

CascadedGaze: Efficiency in Global Context Extraction for Image Restoration

26 Jan 2024arXiv:2401.15235archive 2025-07-28

Amirhosein Ghasemabadi, Muhammad Kamran Janjua, Mohammad Salameh, Chunhua Zhou, Fengyu Sun, Di Niu

Image restoration tasks traditionally rely on convolutional neural networks. However, given the local nature of the convolutional operator, they struggle to capture global information. The promise of attention mechanisms in Transformers is to circumvent this problem, but it comes at the cost of intensive computational overhead. Many recent studies in image restoration have focused on solving the challenge of balancing performance and computational cost via Transformer variants. In this paper, we present CascadedGaze Network (CGNet), an encoder-decoder architecture that employs Global Context Extractor (GCE), a novel and efficient way to capture global information for image restoration. The GCE module leverages small kernels across convolutional layers to learn global dependencies, without requiring self-attention. Extensive experimental results show that our computationally efficient approach performs competitively to a range of state-of-the-art methods on synthetic image denoising and single image deblurring tasks, and pushes the performance boundary further on the real image denoising task.

PaperPDFCodeCode 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="2401.15235")

Code

Syntology Ran 10 of 11 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 2 ran · our draft was wrong; 8 ran with no contract checked.

By repository: official repository: 11 samples from 1 repository, 10 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Ascend-Research/CascadedGaze officialmentioned in papermentioned on GitHubpytorchMIT 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

11 samples harvested; 10 ran; 0 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · our draft was wrong
8ran
1unverified

Licence: 0 of the 11 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 Ascend-Research/CascadedGaze. “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.

calculate_fid Ascend-Research/CascadedGaze/basicsr/metrics/fid.py official repository ran MIT (permissive) · 1d7ce6d6dd7ff5c1 · report
compute_feature Ascend-Research/CascadedGaze/basicsr/metrics/niqe.py official repository ran MIT (permissive) · 5170ff1c4106b27a · report
estimate_aggd_param Ascend-Research/CascadedGaze/basicsr/metrics/niqe.py official repository ran MIT (permissive) · a1282a48b0941f5d · report
extract_inception_features Ascend-Research/CascadedGaze/basicsr/metrics/fid.py official repository ran MIT (permissive) · c9fb213c957dc82d · report
flow_warp Ascend-Research/CascadedGaze/basicsr/models/archs/arch_util.py official repository ran · our draft was wrong MIT (permissive) · ef9faf68f492a375 · report
get_position_from_periods Ascend-Research/CascadedGaze/basicsr/models/lr_scheduler.py official repository ran fingerprinted MIT (permissive) · cd569444547de84f · report
make_layer Ascend-Research/CascadedGaze/basicsr/models/archs/arch_util.py official repository ran · our draft was wrong MIT (permissive) · 96ad5dc9ca239aec · report
prepare_for_ssim Ascend-Research/CascadedGaze/basicsr/metrics/psnr_ssim.py official repository ran fingerprinted MIT (permissive) · 95c6eba9350a455a · report
reorder_image Ascend-Research/CascadedGaze/basicsr/metrics/metric_util.py official repository ran MIT (permissive) · 95067518dc16b3e5 · report
resize_flow Ascend-Research/CascadedGaze/basicsr/models/archs/arch_util.py official repository ran MIT (permissive) · 5a1d8458dc7077a6 · report
niqe Ascend-Research/CascadedGaze/basicsr/metrics/niqe.py official repository unverified MIT (permissive) · 0029cb1566e47350 · report

Tasks

DeblurringDecoderDenoisingImage DeblurringImage DenoisingImage RestorationSingle Image Deblurring

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Deblurring GoPro CGNet PSNR 33.77 #13 of 55 Archive leaderboard report
Image Deblurring GoPro CGNet SSIM 0.968 #13 of 55 Archive leaderboard report
Image Denoising SIDD CGNet PSNR (sRGB) 40.39 #1 of 22 Archive leaderboard report
Image Denoising SIDD CGNet SSIM (sRGB) 0.964 #1 of 22 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