SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2003.04716 · 2020

Deep Blind Video Super-resolution

arXiv · PDF · Open in the Atlas

Code that ran

11 of 15 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; 4 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 6 failures of our instrument; 4 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/2003.04716.json · badge: /api/ran/2003.04716.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
csbhr/Deep-Blind-VSR canonical (classifier label)
classifier basis: census
11 ran · 4 no recorded run
FunctionStatusWhere it lives
Backward Ran
ran; our contract draft was wrong, not the code
csbhr/Deep-Blind-VSR/code/model/flow_pwc.py
pointer only (licence: MIT); the stored copy get_code serves, from xjtu-cvlab-lowlevel/rnn-mbp, is pointer only (licence: NONE) · get_code("8509275d3bfff1d0")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from xjtu-cvlab-lowlevel/rnn-mbp, and GitHub detected no licence in that repository 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.

c2c Ran
ran, honoured the contract we drafted
csbhr/Deep-Blind-VSR/code/model/utils_fft.py
code served (permissive licence) · get_code("30e7c61b0ccdb5ad")
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 3, dtype family float, shape (2, 4, 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 numpy as np

torch.manual_seed(0)

# The function c2c takes a complex numpy array x and converts it to a torch tensor
# It extracts real and imaginary parts and stacks them along the last axis
# So we need to provide a complex numpy array

# Create a small complex numpy array
complex_array = np.array([
    [1.0 + 2.0j, 3.0 + 4.0j, 5.0 + 6.0j, 7.0 + 8.0j],
    [9.0 + 10.0j, 11.0 + 12.0j, 13.0 + 14.0j, 15.0 + 16.0j]
], dtype=np.complex64)

ARGS = {
    'x': complex_array
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float, shape (2, 4, 2) — shape (2, 4, 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
get_act Ran
ran; our contract draft was wrong, not the code
csbhr/Deep-Blind-VSR/code/model/blocks.py
pointer only (licence: MIT); the stored copy get_code serves, from xy-boy/blind-satellite-vsr, is pointer only (licence: NONE) · get_code("9d45f748f3832a1f")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from xy-boy/blind-satellite-vsr, and GitHub detected no licence in that repository 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_blur_kernel Ran
ran on a synthesized input
csbhr/Deep-Blind-VSR/code/script_gene_dataset.py
code served (permissive licence) · get_code("2d06bc62983ab57c")
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 ndarray, ndim 2, dtype family float, shape (11, 11) 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 numpy as np
import random
import math

# Set seed for reproducibility
random.seed(0)

# The function get_blur_kernel takes one parameter: trian (boolean)
# It uses this parameter to decide which gaussian_sigma to pick
# When trian=True, it randomly chooses from a list of sigmas
# When trian=False, it uses sigma=2.0
# The function returns a 2D gaussian kernel (numpy array)

ARGS = {
    "trian": True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (11, 11) — shape (11, 11) 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
get_norm Ran
ran; our contract draft was wrong, not the code
csbhr/Deep-Blind-VSR/code/model/blocks.py
pointer only (licence: MIT); the stored copy get_code serves, from xy-boy/blind-satellite-vsr, is pointer only (licence: NONE) · get_code("d4d29aac211d1ccc")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from xy-boy/blind-satellite-vsr, and GitHub detected no licence in that repository 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_same_padding Ran
ran, honoured the contract we drafted
csbhr/Deep-Blind-VSR/code/model/blocks.py
pointer only (licence: MIT); the stored copy get_code serves, from xy-boy/blind-satellite-vsr, is pointer only (licence: NONE) · get_code("4ec1f46edd412686")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from xy-boy/blind-satellite-vsr, and GitHub detected no licence in that repository 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.

kernel2png Ran
ran, honoured the contract we drafted
csbhr/Deep-Blind-VSR/code/script_gene_dataset.py
pointer only (licence: MIT); the stored copy get_code serves, from xy-boy/blind-satellite-vsr, is pointer only (licence: NONE) · get_code("36142f054164f733")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from xy-boy/blind-satellite-vsr, and GitHub detected no licence in that repository 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.

make_model Ran
ran; our contract draft was wrong, not the code
csbhr/Deep-Blind-VSR/code/model/kernel.py
code served (permissive licence) · get_code("ee5cd3a09717005c")
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 KernelNet. It ran in syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1) at 2026-09-27T00:55:05Z. 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
import torch.nn as nn

torch.manual_seed(0)

class Args:
    def __init__(self):
        self.est_ksize = 13

ARGS = {
    'args': Args()
}
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 KernelNet — a KernelNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a KernelNet output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1); 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
matlab_style_gauss2D Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
csbhr/Deep-Blind-VSR/code/script_gene_dataset.py
pointer only (licence: MIT); the stored copy get_code serves, from xy-boy/blind-satellite-vsr, is pointer only (licence: NONE) · get_code("28ff9e1e5937defa")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from xy-boy/blind-satellite-vsr, and GitHub detected no licence in that repository 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.

r2c Ran
ran, honoured the contract we drafted
csbhr/Deep-Blind-VSR/code/model/utils_fft.py
code served (permissive licence) · get_code("3a47878a83b2d0ed")
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 3, dtype family float, shape (2, 4, 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

torch.manual_seed(0)

# The function r2c takes a real tensor x and converts it to complex
# by stacking it with zeros along the last dimension
# Parameter: x - a real-valued tensor

x = torch.randn(2, 4)

ARGS = {
    "x": x
}
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 3, dtype family float, shape (2, 4, 2) — shape (2, 4, 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
splits Ran
ran; our contract draft was wrong, not the code
csbhr/Deep-Blind-VSR/code/model/utils_fft.py
code served (permissive licence) · get_code("bb9dc6b4b21ead20")
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 6, dtype family float, shape (2, 4, 3, 4, 2, 4) 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)

# Create a tensor with shape NxCxWxHx2
# N=2 (batch), C=4 (channels), W=6 (width), H=8 (height), 2 (last dimension)
a = torch.randn(2, 4, 6, 8, 2)

# Split factor
sf = 2

ARGS = {
    "a": a,
    "sf": sf,
}
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 6, dtype family float, shape (2, 4, 3, 4, 2, 4) — shape (2, 4, 3, 4, 2, 4) 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
cupy_kernel Not yet run
unverified (harvested, no recorded run)
csbhr/Deep-Blind-VSR/code/model/correlation/correlation.py
pointer only (licence: MIT); the stored copy get_code serves, from xjtu-cvlab-lowlevel/rnn-mbp, is pointer only (licence: NONE) · get_code("262657b0ce1b117c")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from xjtu-cvlab-lowlevel/rnn-mbp, and GitHub detected no licence in that repository 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.

deconv_batch Not yet run
unverified (harvested, no recorded run)
csbhr/Deep-Blind-VSR/code/model/deconv_fft.py
code served (permissive licence) · get_code("337e4fc810c76e0b")
How it ran

no invocation recorded.

deconv_sisr_L2_fft Not yet run
unverified (harvested, no recorded run)
csbhr/Deep-Blind-VSR/code/model/deconv_fft.py
code served (permissive licence) · get_code("6fee3d72011125ca")
How it ran

no invocation recorded.

make_model Not yet run
unverified (harvested, no recorded run)
csbhr/Deep-Blind-VSR/code/model/flow_pwc.py
pointer only (licence: MIT); the stored copy get_code serves, from xy-boy/blind-satellite-vsr, is pointer only (licence: NONE) · get_code("3d1acf751ad881a5")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from xy-boy/blind-satellite-vsr, and GitHub detected no licence in that repository 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 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 13 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 3 the same month, 13 later) and 2 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
cupy_kernel 6 other papers
1 dated earlier, 5 later
1812.06264 (2018-12)
Hierarchical Discrete Distribution Decomposition for Match Density Estimation
2004.02501 (2020-04)
Cascaded Deep Video Deblurring Using Temporal Sharpness Prior
2006.13240 (2020-06)
Neural Non-Rigid Tracking
and 3 more not named here
r2c 4 other papers
1 the same month, 3 later
2003.10428 (2020-03)
Deep Unfolding Network for Image Super-Resolution
2104.03078 (2021-04)
Universal and Flexible Optical Aberration Correction Using Deep-Prior Based Deconvolution
2401.07139 (2024-01)
Deep Blind Super-Resolution for Satellite Video
and 1 more not named here
splits 4 other papers
1 the same month, 3 later
2003.10428 (2020-03)
Deep Unfolding Network for Image Super-Resolution
2104.03078 (2021-04)
Universal and Flexible Optical Aberration Correction Using Deep-Prior Based Deconvolution
2401.07139 (2024-01)
Deep Blind Super-Resolution for Satellite Video
and 1 more not named here
Backward 3 other papers
3 later
2004.02501 (2020-04)
Cascaded Deep Video Deblurring Using Temporal Sharpness Prior
2112.05150 (2021-12)
Deep Recurrent Neural Network with Multi-scale Bi-directional Propagation for Video Deblurring
2401.07139 (2024-01)
Deep Blind Super-Resolution for Satellite Video
c2c 3 other papers
1 the same month, 2 later
2003.10428 (2020-03)
Deep Unfolding Network for Image Super-Resolution
2401.07139 (2024-01)
Deep Blind Super-Resolution for Satellite Video
2404.15620 (2024-04)
A Dynamic Kernel Prior Model for Unsupervised Blind Image Super-Resolution
get_same_padding 3 other papers
3 later
2004.02501 (2020-04)
Cascaded Deep Video Deblurring Using Temporal Sharpness Prior
2207.10852 (2022-07)
Spatio-Temporal Deformable Attention Network for Video Deblurring
2401.07139 (2024-01)
Deep Blind Super-Resolution for Satellite Video
deconv_batch 1 other paper
1 later
2401.07139 (2024-01)
Deep Blind Super-Resolution for Satellite Video
get_act 1 other paper
1 later
2401.07139 (2024-01)
Deep Blind Super-Resolution for Satellite Video
get_norm 1 other paper
1 later
2401.07139 (2024-01)
Deep Blind Super-Resolution for Satellite Video
kernel2png 1 other paper
1 later
2401.07139 (2024-01)
Deep Blind Super-Resolution for Satellite Video
make_model 1 other paper
1 later
2401.07139 (2024-01)
Deep Blind Super-Resolution for Satellite Video
make_model 1 other paper
1 later
2401.07139 (2024-01)
Deep Blind Super-Resolution for Satellite Video
matlab_style_gauss2D 1 other paper
1 later
2401.07139 (2024-01)
Deep Blind Super-Resolution for Satellite Video

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

Existing video super-resolution (SR) algorithms usually assume that the blur kernels in the degradation process are known and do not model the blur kernels in the restoration. However, this assumption does not hold for video SR and usually leads to over-smoothed super-resolved images. In this paper, we propose a deep convolutional neural network (CNN) model to solve video SR by a blur kernel modeling approach. The proposed deep CNN model consists of motion blur estimation, motion estimation, and latent image restoration modules. The motion blur estimation module is used to provide reliable blur kernels. With the estimated blur kernel, we develop an image deconvolution method based on the image formation model of video SR to generate intermediate latent images so that some sharp image contents can be restored well. However, the generated intermediate latent images may contain artifacts. To generate high-quality images, we use the motion estimation module to explore the information from adjacent frames, where the motion estimation can constrain the deep CNN model for better image restoration. We show that the proposed algorithm is able to generate clearer images with finer structural details. Extensive experimental results show that the proposed algorithm performs favorably against state-of-the-art methods.

For agents

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

get_harvested_code_for_paper("2003.04716")
get_code_for_paper("2003.04716")
have("2003.04716")

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

curl https://syntology.ai/api/ran/2003.04716.json

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

[![Syntology run record](https://syntology.ai/api/ran/2003.04716.svg)](https://syntology.ai/paper/2003.04716)

Connect an agent — have() is free.