SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.08171 · AAAI · 2024

Deep Linear Array Pushbroom Image Restoration: A Degradation Pipeline and Jitter-Aware Restoration Network

Qi Li, Shiqi Chen, Haoying Li, Ziran Zhang, Huajun Feng, Zhihai Xu, Zida Chen, Menghao Li, Yueting Chen

arXiv · PDF · Open in the Atlas

Code that ran

5 of 8 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 5 failures of our instrument; 3 no recorded run), 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/2401.08171.json · badge: /api/ran/2401.08171.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
JHW2000/JARNet community
Papers with Code archive
5 ran · 3 no recorded run
FunctionStatusWhere it lives
flow_warp Ran
ran; our contract draft was wrong, not the code
JHW2000/JARNet/basicsr/models/archs/jarnet_arch.py
code served (permissive licence) · get_code("da089fa07c3ea836")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 4, dtype family float, shape (2, 4, 3, 5) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn.functional as F

torch.manual_seed(0)

# x: input tensor with shape (batch, channels, height, width)
# flow: optical flow tensor with shape (batch, height, width, 2)
# interp_mode: interpolation mode string
# padding_mode: padding mode string
# align_corners: boolean flag

batch_size = 2
channels = 4
height = 3
width = 5

# Create input tensor x with shape (batch, channels, height, width)
x = torch.randn(batch_size, channels, height, width)

# Create flow tensor with shape (batch, height, width, 2)
# The last dimension is 2 for (x, y) displacement
flow = torch.randn(batch_size, height, width, 2)

ARGS = {
    'x': x,
    'flow': flow,
    'interp_mode': 'bilinear',
    'padding_mode': 'zeros',
    'align_corners': True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (2, 4, 3, 5) — shape (2, 4, 3, 5) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
window_partitions Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
JHW2000/JARNet/basicsr/models/archs/jarnet_arch.py
code served (permissive licence) · get_code("fc1fb34133fbe733")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 4, dtype family float, shape (24, 4, 2, 2) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Create a small input tensor with shape (B, C, H, W)
# B=2 (batch), C=4 (channels), H=8 (height), W=6 (width)
# These dimensions are chosen so they're divisible by window_size
x = torch.randn(2, 4, 8, 6)

# Window size as an integer
window_size = 2

ARGS = {
    "x": x,
    "window_size": window_size,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (24, 4, 2, 2) — shape (24, 4, 2, 2) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
window_partitionx Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
JHW2000/JARNet/basicsr/models/archs/jarnet_arch.py
code served (permissive licence) · get_code("0237e2c8c671688e")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create a small input tensor with shape (B, C, H, W)
# B=2 (batch), C=4 (channels), H=8 (height), W=8 (width)
x = torch.randn(2, 4, 8, 8)

# Window size as an integer
window_size = 4

ARGS = {
    "x": x,
    "window_size": window_size,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
window_reverses Ran
ran; our contract draft was wrong, not the code
JHW2000/JARNet/basicsr/models/archs/jarnet_arch.py
code served (permissive licence) · get_code("93aeadff775de009")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 4, dtype family float, shape (2, 4, 16, 24) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Parameters for window_reverses function
# windows: (num_windows*B, C, window_size, window_size)
# window_size: int or list
# H: height of image
# W: width of image

B = 2  # batch size
C = 4  # number of channels
window_size = 8
H = 16  # image height
W = 24  # image width

# Calculate num_windows
num_windows_h = H // window_size
num_windows_w = W // window_size
num_windows = num_windows_h * num_windows_w

# Create windows tensor: (num_windows*B, C, window_size, window_size)
windows = torch.randn(num_windows * B, C, window_size, window_size)

ARGS = {
    "windows": windows,
    "window_size": window_size,
    "H": H,
    "W": W,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (2, 4, 16, 24) — shape (2, 4, 16, 24) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
window_reversex Ran
ran; our contract draft was wrong, not the code
JHW2000/JARNet/basicsr/models/archs/jarnet_arch.py
code served (permissive licence) · get_code("f7c51e5750d02638")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 4, dtype family float, shape (1, 3, 8, 8) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Parameters for window_reversex
# windows: (num_windows*B, C, window_size, window_size)
# window_size: int
# H: int (height of image)
# W: int (width of image)
# batch_list: list of batch indices

window_size = 4
H = 8
W = 8
C = 3
B = 2

# Create windows tensor
# For a simple case with batch_list of length 2 (w != W case)
# num_windows = (H // window_size) * (W // window_size) = 2 * 2 = 4
# So windows shape should be (4*B, C, window_size, window_size) = (8, 3, 4, 4)
num_windows = (H // window_size) * (W // window_size)
windows = torch.randn(num_windows * B, C, window_size, window_size)

# batch_list determines how the windows are split
# For len(batch_list) == 2, we have two segments
# batch_list[0] is the split point between main and right windows
batch_list = [num_windows * B // 2, num_windows * B]

ARGS = {
    "windows": windows,
    "window_size": window_size,
    "H": H,
    "W": W,
    "batch_list": batch_list,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (1, 3, 8, 8) — shape (1, 3, 8, 8) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
JARNet Not yet run
unverified (harvested, no recorded run)
JHW2000/JARNet/basicsr/models/archs/jarnet_arch.py
code served (permissive licence) · get_code("7fc1e84e19fc8d23")
How it ran

no invocation recorded.

SFResBlock Not yet run
unverified (harvested, no recorded run)
JHW2000/JARNet/basicsr/models/archs/jarnet_arch.py
code served (permissive licence) · get_code("cdf06b13ce7688ca")
How it ran

no invocation recorded.

fft_bench_complex_mlp Not yet run
unverified (harvested, no recorded run)
JHW2000/JARNet/basicsr/models/archs/jarnet_arch.py
code served (permissive licence) · get_code("78848daf166ca48a")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 4 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 4 later) and 4 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
flow_warp
brick of this paper's assembly: helper
25 other papers
7 dated earlier, 1 the same month, 16 later, 1 same year, order not determinable · 1 only as an assembly brick
2107.10833 (2021-07)
Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data
2303.06373 (2023-03)
Recursive Generalization Transformer for Image Super-Resolution
and 22 more not named here
window_partitionx
brick of this paper's assembly: helper
3 other papers
3 later
2404.01547 (2024-04)
Bidirectional Multi-Scale Implicit Neural Representations for Image Deraining
2404.13153 (2024-04)
Motion-adaptive Separable Collaborative Filters for Blind Motion Deblurring
2406.09135 (2024-06)
AdaRevD: Adaptive Patch Exiting Reversible Decoder Pushes the Limit of Image Deblurring
window_partitions
brick of this paper's assembly: helper
2 other papers
2 later
2404.01547 (2024-04)
Bidirectional Multi-Scale Implicit Neural Representations for Image Deraining
2406.09135 (2024-06)
AdaRevD: Adaptive Patch Exiting Reversible Decoder Pushes the Limit of Image Deblurring
window_reverses
brick of this paper's assembly: helper
2 other papers
2 later
2404.01547 (2024-04)
Bidirectional Multi-Scale Implicit Neural Representations for Image Deraining
2406.09135 (2024-06)
AdaRevD: Adaptive Patch Exiting Reversible Decoder Pushes the Limit of Image Deblurring

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

Linear Array Pushbroom (LAP) imaging technology is widely used in the realm of remote sensing. However, images acquired through LAP always suffer from distortion and blur because of camera jitter. Traditional methods for restoring LAP images, such as algorithms estimating the point spread function (PSF), exhibit limited performance. To tackle this issue, we propose a Jitter-Aware Restoration Network (JAR-Net), to remove the distortion and blur in two stages. In the first stage, we formulate an Optical Flow Correction (OFC) block to refine the optical flow of the degraded LAP images, resulting in pre-corrected images where most of the distortions are alleviated. In the second stage, for further enhancement of the pre-corrected images, we integrate two jitteraware techniques within the Spatial and Frequency Residual (SFRes) block: 1) introducing Coordinate Attention (CoA) to the SFRes block in order to capture the jitter state in orthogonal direction; 2) manipulating image features in both spatial and frequency domains to leverage local and global priors. Additionally, we develop a data synthesis pipeline, which applies Continue Dynamic Shooting Model (CDSM) to simulate realistic degradation in LAP images. Both the proposed JARNet and LAP image synthesis pipeline establish a foundation for addressing this intricate challenge. Extensive experiments demonstrate that the proposed two-stage method outperforms state-of-the-art image restoration models. Code is available at https://github.com/JHW2000/JARNet.

For agents

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

get_harvested_code_for_paper("2401.08171")
get_code_for_paper("2401.08171")
have("2401.08171")

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

curl https://syntology.ai/api/ran/2401.08171.json

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

[![Syntology run record](https://syntology.ai/api/ran/2401.08171.svg)](https://syntology.ai/paper/2401.08171)

Connect an agent — have() is free.