SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2102.02808 · CVPR · 2021

Multi-Stage Progressive Image Restoration

Ming-Hsuan Yang, Ling Shao, Salman Khan, Munawar Hayat, Shahbaz Fahad, Khan, Syed Waqas Zamir, Aditya Arora

arXiv · PDF · Open in the Atlas

Code that ran

18 of 26 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (13 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 17 have no contract verdict; 1 failure of our instrument; 8 no recorded run), measured 2026-11-21; 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/2102.02808.json · badge: /api/ran/2102.02808.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
swz30/mirnetv2 community
Papers with Code archive
8 ran · 2 no recorded run
swz30/CycleISP community
Papers with Code archive
5 ran · 0 no recorded run
taowangzj/llformer community
Papers with Code archive
3 ran · 3 no recorded run
swz30/MPRNet marked official in Papers with Code
Papers with Code archive
2 ran · 2 no recorded run
swz30/restormer community
Papers with Code archive
0 ran · 1 no recorded run
FunctionStatusWhere it lives
ContextBlock Ran
ran on a synthesized input · constructed an object; no result was computed
swz30/mirnetv2/basicsr/models/archs/mirnet_v2_arch.py
pointer only (licence: NOASSERTION) · get_code("9905ed97879ec410")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, swz30/mirnetv2 (NOASSERTION). 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.

DAB Ran
ran on a synthesized input · constructed an object; no result was computed
swz30/CycleISP/networks/denoising_rgb.py
pointer only (licence: NOASSERTION) · get_code("fc4aa1da5676f5f6")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, swz30/CycleISP (NOASSERTION). 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.

DenoiseNet Ran
ran on a synthesized input · constructed an object; no result was computed
swz30/CycleISP/networks/denoising_rgb.py
pointer only (licence: NOASSERTION) · get_code("3803599e00731bf3")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, swz30/CycleISP (NOASSERTION). 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.

Down Ran
ran on a synthesized input · constructed an object; no result was computed
swz30/mirnetv2/basicsr/models/archs/mirnet_v2_arch.py
pointer only (licence: NOASSERTION) · get_code("95877fdf404e7e2d")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, swz30/mirnetv2 (NOASSERTION). 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
swz30/mirnetv2/basicsr/models/archs/mirnet_v2_arch.py
pointer only (licence: NOASSERTION) · get_code("823880bb4a4fd803")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, swz30/mirnetv2 (NOASSERTION). 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.

FeedForward Ran
ran on a synthesized input
taowangzj/llformer/model/LLFormer.py
pointer only (licence: NOASSERTION) · get_code("2e4380a675a7a636")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, taowangzj/llformer (NOASSERTION). 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.

MRB Ran
ran on a synthesized input · constructed an object; no result was computed
swz30/mirnetv2/basicsr/models/archs/mirnet_v2_arch.py
pointer only (licence: NOASSERTION) · get_code("9f0ec2d0ebd79268")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, swz30/mirnetv2 (NOASSERTION). 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.

NextAttentionImplZ Ran
ran on a synthesized input
taowangzj/llformer/model/LLFormer.py
pointer only (licence: NOASSERTION) · get_code("dcfcd2cfc0518597")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, taowangzj/llformer (NOASSERTION). 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.

NextAttentionZ Ran
ran on a synthesized input
taowangzj/llformer/model/LLFormer.py
pointer only (licence: NOASSERTION) · get_code("f3c858250a132490")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, taowangzj/llformer (NOASSERTION). 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.

ORB Ran
ran on a synthesized input · constructed an object; no result was computed
swz30/MPRNet/Deblurring/MPRNet.py
pointer only (licence: NOASSERTION) · get_code("0248b30780d949dc")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, swz30/MPRNet (NOASSERTION). 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.

RCB Ran
ran on a synthesized input · constructed an object; no result was computed
swz30/mirnetv2/basicsr/models/archs/mirnet_v2_arch.py
pointer only (licence: NOASSERTION) · get_code("92fe045c36c149b1")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, swz30/mirnetv2 (NOASSERTION). 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.

RRG Ran
ran on a synthesized input · constructed an object; no result was computed
swz30/CycleISP/networks/denoising_rgb.py
pointer only (licence: NOASSERTION) · get_code("69df2e5e6ab1bfad")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, swz30/CycleISP (NOASSERTION). 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
swz30/mirnetv2/basicsr/models/archs/mirnet_v2_arch.py
pointer only (licence: NOASSERTION) · get_code("cecd263c57a13552")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, swz30/mirnetv2 (NOASSERTION). 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.

Up Ran
ran on a synthesized input · constructed an object; no result was computed
swz30/mirnetv2/basicsr/models/archs/mirnet_v2_arch.py
pointer only (licence: NOASSERTION) · get_code("1c8472333e5c2601")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, swz30/mirnetv2 (NOASSERTION). 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
swz30/MPRNet/Deblurring/MPRNet.py
pointer only (licence: NOASSERTION) · get_code("6f67ba4ae094dbdf")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, swz30/MPRNet (NOASSERTION). 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
swz30/mirnetv2/basicsr/models/archs/mirnet_v2_arch.py
pointer only (licence: NOASSERTION) · get_code("7ad799995cd1b005")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, swz30/mirnetv2 (NOASSERTION). 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.

conv Ran
ran; our contract draft was wrong, not the code
swz30/CycleISP/networks/denoising_rgb.py
pointer only (licence: NOASSERTION) · get_code("dddca40fb4dbccdc")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, swz30/CycleISP (NOASSERTION). 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.

spatial_attn_layer Ran
ran on a synthesized input
swz30/CycleISP/networks/denoising_rgb.py
pointer only (licence: NOASSERTION) · get_code("55ca1005128011e2")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, swz30/CycleISP (NOASSERTION). 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.

LAM_Module_v2 Not yet run
unverified (harvested, no recorded run)
taowangzj/llformer/model/LLFormer.py
pointer only (licence: NOASSERTION) · get_code("df51bfb12d6bab5a")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, taowangzj/llformer (NOASSERTION). 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.

LLFormer Not yet run
unverified (harvested, no recorded run)
taowangzj/llformer/model/LLFormer.py
pointer only (licence: NOASSERTION) · get_code("e1acb5598af874ea")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, taowangzj/llformer (NOASSERTION). 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.

MIRNet_v2 Not yet run
unverified (harvested, no recorded run)
swz30/mirnetv2/basicsr/models/archs/mirnet_v2_arch.py
pointer only (licence: NOASSERTION) · get_code("e229ec6cd3be0368")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, swz30/mirnetv2 (NOASSERTION). 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.

MPRNet Not yet run
unverified (harvested, no recorded run)
swz30/MPRNet/Deblurring/MPRNet.py
pointer only (licence: NOASSERTION) · get_code("f07bf53bd31a377c")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, swz30/MPRNet (NOASSERTION). 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.

ORSNet Not yet run
unverified (harvested, no recorded run)
swz30/MPRNet/Deblurring/MPRNet.py
pointer only (licence: NOASSERTION) · get_code("e3f5a4be55c14019")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, swz30/MPRNet (NOASSERTION). 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.

RRG Not yet run
unverified (harvested, no recorded run)
swz30/mirnetv2/basicsr/models/archs/mirnet_v2_arch.py
pointer only (licence: NOASSERTION) · get_code("ab472a2ed659eb18")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, swz30/mirnetv2 (NOASSERTION). 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.

Restormer Not yet run
unverified (harvested, no recorded run)
swz30/restormer/basicsr/models/archs/restormer_arch.py
code served (permissive licence) · get_code("266026630c2bfcd7")
How it ran

no invocation recorded.

TransformerBlock Not yet run
unverified (harvested, no recorded run)
taowangzj/llformer/model/LLFormer.py
pointer only (licence: NOASSERTION) · get_code("2d417e1b35e33481")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, taowangzj/llformer (NOASSERTION). 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, 5 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 5 later) and 21 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
ORB
brick of this paper's assembly: model
1 other paper
1 later · 1 only as an assembly brick
2303.15046 (2023-03)
Nighttime Smartphone Reflective Flare Removal Using Optical Center Symmetry Prior
ORSNet
brick of this paper's assembly: model
1 other paper
1 later · 1 only as an assembly brick
2303.15046 (2023-03)
Nighttime Smartphone Reflective Flare Removal Using Optical Center Symmetry Prior
UpSample
brick of this paper's assembly: model
1 other paper
1 later · 1 only as an assembly brick
2303.15046 (2023-03)
Nighttime Smartphone Reflective Flare Removal Using Optical Center Symmetry Prior
conv
brick of this paper's assembly: helper
1 other paper
1 later
2403.06098 (2024-03)
A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Models
spatial_attn_layer
brick of this paper's assembly: model
1 other paper
1 later
2503.18703 (2025-03)
Channel Consistency Prior and Self-Reconstruction Strategy Based Unsupervised Image Deraining

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 2026-11-21.

Repositories linked to this paper

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

Abstract

Image restoration tasks demand a complex balance between spatial details and high-level contextualized information while recovering images. In this paper, we propose a novel synergistic design that can optimally balance these competing goals. Our main proposal is a multi-stage architecture, that progressively learns restoration functions for the degraded inputs, thereby breaking down the overall recovery process into more manageable steps. Specifically, our model first learns the contextualized features using encoder-decoder architectures and later combines them with a high-resolution branch that retains local information. At each stage, we introduce a novel per-pixel adaptive design that leverages in-situ supervised attention to reweight the local features. A key ingredient in such a multi-stage architecture is the information exchange between different stages. To this end, we propose a twofaceted approach where the information is not only exchanged sequentially from early to late stages, but lateral connections between feature processing blocks also exist to avoid any loss of information. The resulting tightly interlinked multi-stage architecture, named as MPRNet, delivers strong performance gains on ten datasets across a range of tasks including image deraining, deblurring, and denoising. The source code and pre-trained models are available at https://github.com/swz30/MPRNet.

For agents

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

get_harvested_code_for_paper("2102.02808")
get_code_for_paper("2102.02808")
have("2102.02808")

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

curl https://syntology.ai/api/ran/2102.02808.json

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

[![Syntology run record](https://syntology.ai/api/ran/2102.02808.svg)](https://syntology.ai/paper/2102.02808)

Connect an agent — have() is free.