SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2308.14036 · ICCV · 2023

MB-TaylorFormer: Multi-branch Efficient Transformer Expanded by Taylor Formula for Image Dehazing

Kaihao Zhang, Hongdong Li, Zhi Jin, Wenhan Luo, Chenxi Wang, Yuwei Qiu

arXiv · PDF · Open in the Atlas

Code that ran

22 of 26 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (7 of them constructed an object rather than computing a result; 6 honoured the contract we drafted, 0 violated it and 9 have no contract verdict; 7 failures of our instrument; 4 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2308.14036.json · badge: /api/ran/2308.14036.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
fvl2020/iccv-2023-mb-taylorformer canonical (classifier label)
classifier basis: census
13 ran · 1 no recorded run
FVL2020/ICCV-2023-MB-TaylorFormer community
Papers with Code archive
9 ran · 3 no recorded run
FunctionStatusWhere it lives
count_param Ran
ran, honoured the contract we drafted
fvl2020/iccv-2023-mb-taylorformer/basicsr/models/archs/MB_TaylorFormer.py
pointer only (licence: NONE); the stored copy get_code serves, from FVL2020/ICCV-2023-MB-TaylorFormer, is pointer only (licence: NONE) · get_code("afd3c5ab4cb8face")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fvl2020/iccv-2023-mb-taylorformer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Attention Ran
ran on a synthesized input · constructed an object; no result was computed
FVL2020/ICCV-2023-MB-TaylorFormer/basicsr/models/archs/MB_TaylorFormer.py
pointer only (licence: NONE) · get_code("659261b010a72668")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, FVL2020/ICCV-2023-MB-TaylorFormer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

DWCPatchEmbed Ran
ran on a synthesized input · constructed an object; no result was computed
FVL2020/ICCV-2023-MB-TaylorFormer/basicsr/models/archs/MB_TaylorFormer.py
pointer only (licence: NONE) · get_code("7e12b4a365754bb3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, FVL2020/ICCV-2023-MB-TaylorFormer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

DWConv2d_BN Ran
ran on a synthesized input · constructed an object; no result was computed
FVL2020/ICCV-2023-MB-TaylorFormer/basicsr/models/archs/MB_TaylorFormer.py
pointer only (licence: NONE) · get_code("64cd61fee6349de6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, FVL2020/ICCV-2023-MB-TaylorFormer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Downsample Ran
ran on a synthesized input · constructed an object; no result was computed
FVL2020/ICCV-2023-MB-TaylorFormer/basicsr/models/archs/MB_TaylorFormer.py
pointer only (licence: NONE) · get_code("428e6e039f598efa")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, FVL2020/ICCV-2023-MB-TaylorFormer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Patch_Embed_stage Ran
ran on a synthesized input · constructed an object; no result was computed
FVL2020/ICCV-2023-MB-TaylorFormer/basicsr/models/archs/MB_TaylorFormer.py
pointer only (licence: NONE) · get_code("2d32326ab1c1db16")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, FVL2020/ICCV-2023-MB-TaylorFormer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

SKFF Ran
ran on a synthesized input · constructed an object; no result was computed
FVL2020/ICCV-2023-MB-TaylorFormer/basicsr/models/archs/MB_TaylorFormer.py
pointer only (licence: NONE) · get_code("03b6adc687eca587")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, FVL2020/ICCV-2023-MB-TaylorFormer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

TransformerBlock Ran
ran on a synthesized input
FVL2020/ICCV-2023-MB-TaylorFormer/basicsr/models/archs/MB_TaylorFormer.py
pointer only (licence: NONE) · get_code("60ff91d683606241")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, FVL2020/ICCV-2023-MB-TaylorFormer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Upsample Ran
ran on a synthesized input · constructed an object; no result was computed
FVL2020/ICCV-2023-MB-TaylorFormer/basicsr/models/archs/MB_TaylorFormer.py
pointer only (licence: NONE) · get_code("5499b5a997e32c0e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, FVL2020/ICCV-2023-MB-TaylorFormer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

calculate_fid Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
fvl2020/iccv-2023-mb-taylorformer/basicsr/metrics/fid.py
pointer only (licence: NONE) · get_code("1d7ce6d6dd7ff5c1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fvl2020/iccv-2023-mb-taylorformer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

calculate_psnr Ran
ran; our contract draft was wrong, not the code
fvl2020/iccv-2023-mb-taylorformer/utils.py
pointer only (licence: NONE); the stored copy get_code serves, from AlifAshrafee/Restoring-Without-Forgetting, is pointer only (licence: NONE) · get_code("d292dd965ab59629")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fvl2020/iccv-2023-mb-taylorformer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

calculate_ssim Ran
ran; our contract draft was wrong, not the code
fvl2020/iccv-2023-mb-taylorformer/utils.py
pointer only (licence: NONE); the stored copy get_code serves, from AlifAshrafee/Restoring-Without-Forgetting, is pointer only (licence: NONE) · get_code("a05b184dc6c264a0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fvl2020/iccv-2023-mb-taylorformer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

compute_feature Ran
ran, honoured the contract we drafted
fvl2020/iccv-2023-mb-taylorformer/basicsr/metrics/niqe.py
pointer only (licence: NONE) · get_code("5170ff1c4106b27a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fvl2020/iccv-2023-mb-taylorformer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

estimate_aggd_param Ran
ran, honoured the contract we drafted
fvl2020/iccv-2023-mb-taylorformer/basicsr/metrics/niqe.py
pointer only (licence: NONE) · get_code("a1282a48b0941f5d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fvl2020/iccv-2023-mb-taylorformer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

extract_inception_features Ran
ran, honoured the contract we drafted
fvl2020/iccv-2023-mb-taylorformer/basicsr/metrics/fid.py
pointer only (licence: NONE) · get_code("c9fb213c957dc82d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fvl2020/iccv-2023-mb-taylorformer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_position_from_periods Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
fvl2020/iccv-2023-mb-taylorformer/basicsr/models/lr_scheduler.py
pointer only (licence: NONE); the stored copy get_code serves, from AlifAshrafee/Restoring-Without-Forgetting, is pointer only (licence: NONE) · get_code("cd569444547de84f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fvl2020/iccv-2023-mb-taylorformer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

refine_att Ran
ran on a synthesized input
FVL2020/ICCV-2023-MB-TaylorFormer/basicsr/models/archs/MB_TaylorFormer.py
pointer only (licence: NONE) · get_code("59ccf227e7c920d2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, FVL2020/ICCV-2023-MB-TaylorFormer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

reorder_image Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
fvl2020/iccv-2023-mb-taylorformer/basicsr/metrics/metric_util.py
pointer only (licence: NONE); the stored copy get_code serves, from AlifAshrafee/Restoring-Without-Forgetting, is pointer only (licence: NONE) · get_code("95067518dc16b3e5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fvl2020/iccv-2023-mb-taylorformer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

ssim Ran
ran, honoured the contract we drafted
fvl2020/iccv-2023-mb-taylorformer/utils.py
pointer only (licence: NONE); the stored copy get_code serves, from AlifAshrafee/Restoring-Without-Forgetting, is pointer only (licence: NONE) · get_code("ba721aeacc165234")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fvl2020/iccv-2023-mb-taylorformer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

ssim_cv2 Ran
ran, honoured the contract we drafted
fvl2020/iccv-2023-mb-taylorformer/Dehazing/calculate_compare.py
pointer only (licence: NONE) · get_code("bbbdfc579e51326c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fvl2020/iccv-2023-mb-taylorformer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

to_3d Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
fvl2020/iccv-2023-mb-taylorformer/basicsr/models/archs/MB_TaylorFormer.py
pointer only (licence: NONE); the stored copy get_code serves, from gladzhang/Xformer, is pointer only (licence: NONE) · get_code("82a15cc1e46f7e4d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fvl2020/iccv-2023-mb-taylorformer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

to_4d Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
fvl2020/iccv-2023-mb-taylorformer/basicsr/models/archs/MB_TaylorFormer.py
pointer only (licence: NONE); the stored copy get_code serves, from gladzhang/Xformer, is pointer only (licence: NONE) · get_code("b20f2a5df739a59e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fvl2020/iccv-2023-mb-taylorformer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

MB_TaylorFormer Not yet run
unverified (harvested, no recorded run)
FVL2020/ICCV-2023-MB-TaylorFormer/basicsr/models/archs/MB_TaylorFormer.py
pointer only (licence: NONE) · get_code("5b4b5591be8c70df")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, FVL2020/ICCV-2023-MB-TaylorFormer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

MHCAEncoder Not yet run
unverified (harvested, no recorded run)
FVL2020/ICCV-2023-MB-TaylorFormer/basicsr/models/archs/MB_TaylorFormer.py
pointer only (licence: NONE) · get_code("579b7505e2f45641")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, FVL2020/ICCV-2023-MB-TaylorFormer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

MHCA_stage Not yet run
unverified (harvested, no recorded run)
FVL2020/ICCV-2023-MB-TaylorFormer/basicsr/models/archs/MB_TaylorFormer.py
pointer only (licence: NONE) · get_code("ed01ae5f23d33199")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, FVL2020/ICCV-2023-MB-TaylorFormer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

niqe Not yet run
unverified (harvested, no recorded run)
fvl2020/iccv-2023-mb-taylorformer/basicsr/metrics/niqe.py
pointer only (licence: NONE) · get_code("0029cb1566e47350")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fvl2020/iccv-2023-mb-taylorformer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 26 samples lifted from this paper's linked repositories, 26 carry a function identity and 0 do not. Of the 26 distinct functions with an identity, 13 are also present in other papers whose code we hold (13 with at least one paper dated earlier, 4 the same month, 12 later) and 13 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
to_3d
brick of this paper's assembly: helper
80 other papers
17 dated earlier, 2 the same month, 59 later, 2 same year, order not determinable · 18 only as an assembly brick
2003.06792 (2020-03)
Learning Enriched Features for Real Image Restoration and Enhancement
2102.02808 (2021-02)
Multi-Stage Progressive Image Restoration
2111.09881 (2021-11)
Restormer: Efficient Transformer for High-Resolution Image Restoration
and 77 more not named here
to_4d
brick of this paper's assembly: helper
79 other papers
17 dated earlier, 2 the same month, 58 later, 2 same year, order not determinable · 18 only as an assembly brick
2003.06792 (2020-03)
Learning Enriched Features for Real Image Restoration and Enhancement
2102.02808 (2021-02)
Multi-Stage Progressive Image Restoration
2111.09881 (2021-11)
Restormer: Efficient Transformer for High-Resolution Image Restoration
and 76 more not named here
get_position_from_periods 55 other papers
10 dated earlier, 2 the same month, 41 later, 2 same year, order not determinable
2110.04627 (2021-10)
Vector-quantized Image Modeling with Improved VQGAN
136790177 (2022 (year only))
Frequency and Spatial Dual Guidance for Image Dehazing
2204.04676 (2022-04)
Simple Baselines for Image Restoration
and 52 more not named here
ssim 18 other papers
10 dated earlier, 8 later
1809.00219 (2018-09)
ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
1904.03377 (2019-04)
Blind Super-Resolution With Iterative Kernel Correction
2005.05650 (2020-05)
Invertible Image Rescaling
and 15 more not named here
reorder_image 17 other papers
2 dated earlier, 1 the same month, 13 later, 1 same year, order not determinable
2204.04676 (2022-04)
Simple Baselines for Image Restoration
2303.06373 (2023-03)
Recursive Generalization Transformer for Image Super-Resolution
and 14 more not named here
calculate_psnr 9 other papers
4 dated earlier, 5 later
Zamir_Restormer_Efficient_Transformer_for_High-Resolution_Image_Restoration_CVPR_2022_paper (2022 (year only))
Restormer: Efficient Transformer for High-Resolution Image Restoration
2201.02973 (2022-01)
MAXIM: Multi-Axis MLP for Image Processing
2303.02881 (2023-03)
KBNet: Kernel Basis Network for Image Restoration
and 6 more not named here
calculate_fid 8 other papers
2 dated earlier, 6 later
2204.04676 (2022-04)
Simple Baselines for Image Restoration
2303.02881 (2023-03)
KBNet: Kernel Basis Network for Image Restoration
2401.00027 (2024-01)
Efficient Multi-scale Network with Learnable Discrete Wavelet Transform for Blind Motion Deblurring
and 5 more not named here
calculate_ssim 8 other papers
4 dated earlier, 4 later
Zamir_Restormer_Efficient_Transformer_for_High-Resolution_Image_Restoration_CVPR_2022_paper (2022 (year only))
Restormer: Efficient Transformer for High-Resolution Image Restoration
2201.02973 (2022-01)
MAXIM: Multi-Axis MLP for Image Processing
2303.02881 (2023-03)
KBNet: Kernel Basis Network for Image Restoration
and 5 more not named here
estimate_aggd_param 8 other papers
1 dated earlier, 5 later, 2 same year, order not determinable
2204.04676 (2022-04)
Simple Baselines for Image Restoration
Chao_Equivalent_Transformation_and_Dual_Stream_Network_Construction_for_Mobile_Image_CVPR_2023_paper (2023 (year only))
Equivalent Transformation and Dual Stream Network Construction for Mobile Image Super-Resolution
and 5 more not named here
extract_inception_features 8 other papers
2 dated earlier, 6 later
2204.04676 (2022-04)
Simple Baselines for Image Restoration
2303.02881 (2023-03)
KBNet: Kernel Basis Network for Image Restoration
2401.00027 (2024-01)
Efficient Multi-scale Network with Learnable Discrete Wavelet Transform for Blind Motion Deblurring
and 5 more not named here
compute_feature 7 other papers
1 dated earlier, 5 later, 1 same year, order not determinable
2204.04676 (2022-04)
Simple Baselines for Image Restoration
2401.00027 (2024-01)
Efficient Multi-scale Network with Learnable Discrete Wavelet Transform for Blind Motion Deblurring
and 4 more not named here
niqe 7 other papers
1 dated earlier, 5 later, 1 same year, order not determinable
2204.04676 (2022-04)
Simple Baselines for Image Restoration
2401.00027 (2024-01)
Efficient Multi-scale Network with Learnable Discrete Wavelet Transform for Blind Motion Deblurring
and 4 more not named here
count_param 3 other papers
3 dated earlier
2106.00487 (2021-06)
Dense Nested Attention Network for Infrared Small Target Detection
2112.05150 (2021-12)
Deep Recurrent Neural Network with Multi-scale Bi-directional Propagation for Video Deblurring
2305.19141 (2023-05)
Taylorformer: Probabilistic Modelling for Random Processes including Time Series

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

In recent years, Transformer networks are beginning to replace pure convolutional neural networks (CNNs) in the field of computer vision due to their global receptive field and adaptability to input. However, the quadratic computational complexity of softmax-attention limits the wide application in image dehazing task, especially for highresolution images. To address this issue, we propose a new Transformer variant, which applies the Taylor expansion to approximate the softmax-attention and achieves linear computational complexity. A multi-scale attention refinement module is proposed as a complement to correct the error of the Taylor expansion. Furthermore, we introduce a multi-branch architecture with multi-scale patch embedding to the proposed Transformer, which embeds features by overlapping deformable convolution of different scales. The design of multi-scale patch embedding is based on three key ideas: 1) various sizes of the receptive field; 2) multilevel semantic information; 3) flexible shapes of the receptive field. Our model, named Multi-branch Transformer expanded by Taylor formula (MB-TaylorFormer), can embed coarse to fine features more flexibly at the patch embedding stage and capture long-distance pixel interactions with limited computational cost. Experimental results on several dehazing benchmarks show that MB-TaylorFormer achieves state-of-the-art (SOTA) performance with a light computational burden. The source code and pre-trained models are available at https://github.com/FVL2020/ICCV-2023-MB-TaylorFormer.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2308.14036")
get_code_for_paper("2308.14036")
have("2308.14036")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2308.14036.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2308.14036.svg)](https://syntology.ai/paper/2308.14036)

Connect an agent — have() is free.