SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1904.03377 · 2019

Blind Super-Resolution With Iterative Kernel Correction

arXiv · PDF · Open in the Atlas

Code that ran

6 of 6 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; 3 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 0 failures of our instrument; 0 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/1904.03377.json · badge: /api/ran/1904.03377.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
yuanjunchai/IKC community (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
Lornatang/SFTMD-PyTorch community (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
FunctionStatusWhere it lives
calculate_psnr Ran
ran, honoured the contract we drafted
yuanjunchai/IKC/metrics/calculate_PSNR_SSIM.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from redrock303/ADF-LLIE, is pointer only (licence: NONE) · get_code("9394ff2c25b8a988")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from redrock303/ADF-LLIE, 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.

calculate_ssim Ran
ran, honoured the contract we drafted
yuanjunchai/IKC/metrics/calculate_PSNR_SSIM.py
code served (permissive licence) · get_code("5aef99e58703c44a")
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 float64, ndim 0, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 cv2

# Create two small test images with values in [0, 255]
# Using distinct sizes to allow shape probing
np.random.seed(0)

# Test case 1: 3D color image (height, width, channels)
img1_3d = np.random.randint(0, 256, size=(32, 32, 3), dtype=np.uint8)
img2_3d = np.random.randint(0, 256, size=(32, 32, 3), dtype=np.uint8)

# Test case 2: 2D grayscale image
img1_2d = np.random.randint(0, 256, size=(32, 32), dtype=np.uint8)
img2_2d = np.random.randint(0, 256, size=(32, 32), dtype=np.uint8)

# Test case 3: 3D single channel image
img1_single = np.random.randint(0, 256, size=(32, 32, 1), dtype=np.uint8)
img2_single = np.random.randint(0, 256, size=(32, 32, 1), dtype=np.uint8)

ARGS = {
    'img1': img1_3d,
    'img2': img2_3d,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
image2tensor Ran
ran on a synthesized input
Lornatang/SFTMD-PyTorch/imgproc.py
code served (permissive licence) · get_code("1df4cd01e272e4cc")
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 (3, 4, 3) 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 torch
from torchvision.transforms import functional as F_vision

torch.manual_seed(0)

# Create a sample image as numpy array
# The function expects an image in format that to_tensor can handle
# to_tensor expects either PIL Image or numpy array with shape (H, W, C) or (H, W)
# For color images, shape should be (H, W, 3) with values in [0, 1] range
image = np.random.rand(4, 3, 3).astype(np.float32)  # 4x3 image with 3 channels, values in [0, 1]

ARGS = {
    "image": image,
    "range_norm": False,
    "half": False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch, torchvision — 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 (3, 4, 3) — shape (3, 4, 3) 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
principal_component_analysis Ran
ran on a synthesized input
Lornatang/SFTMD-PyTorch/imgproc.py
code served (permissive licence) · get_code("b757e6fc17cab8f0")
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 2, dtype family float, shape (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 numpy as np
import torch

torch.manual_seed(0)

# Create small sample data: 2 samples, 4 features
data = np.random.randn(2, 4).astype(np.float32)

ARGS = {
    "data": data,
    "k": 2
}
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 2, dtype family float, shape (4, 2) — shape (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
ssim Ran
ran, honoured the contract we drafted
yuanjunchai/IKC/metrics/calculate_PSNR_SSIM.py
pointer only (licence: Apache-2.0); 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: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from AlifAshrafee/Restoring-Without-Forgetting, 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.

tensor2image Ran
ran on a synthesized input
Lornatang/SFTMD-PyTorch/imgproc.py
code served (permissive licence) · get_code("bc562954fab9c9fb")
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 3, dtype family int, shape (128, 128, 3) 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 small tensor with shape [1, 3, 128, 128] as shown in the docstring example
# Using normalized values in range [-1, 1] or [0, 1]
tensor = torch.randn(1, 3, 128, 128)

ARGS = {
    "tensor": tensor,
    "range_norm": False,
    "half": False,
}
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 ndarray, ndim 3, dtype family int, shape (128, 128, 3) — shape (128, 128, 3) 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

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 3 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
ssim 18 other papers
1 dated earlier, 17 later
1809.00219 (2018-09)
ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
2005.05650 (2020-05)
Invertible Image Rescaling
and 15 more not named here
calculate_psnr 16 other papers
1 dated earlier, 15 later
1809.00219 (2018-09)
ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
1905.02716 (2019-05)
EDVR: Video Restoration with Enhanced Deformable Convolutional Networks
1907.03222 (2019-07)
IRNet: A General Purpose Deep Residual Regression Framework for Materials Discovery
and 13 more not named here
calculate_ssim 3 other papers
1 dated earlier, 2 later
1809.00219 (2018-09)
ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
2005.05650 (2020-05)
Invertible Image Rescaling
2407.09299 (2024-07)
PID: Physics-Informed Diffusion Model for Infrared Image Generation
tensor2image 2 other papers
2 dated earlier
1511.04587 (2015-11)
Accurate Image Super-Resolution Using Very Deep Convolutional Networks
1608.00367 (2016-08)
Accelerating the Super-Resolution Convolutional Neural Network

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

Deep learning based methods have dominated super-resolution (SR) field due to their remarkable performance in terms of effectiveness and efficiency. Most of these methods assume that the blur kernel during downsampling is predefined/known (e.g., bicubic). However, the blur kernels involved in real applications are complicated and unknown, resulting in severe performance drop for the advanced SR methods. In this paper, we propose an Iterative Kernel Correction (IKC) method for blur kernel estimation in blind SR problem, where the blur kernels are unknown. We draw the observation that kernel mismatch could bring regular artifacts (either over-sharpening or over-smoothing), which can be applied to correct inaccurate blur kernels. Thus we introduce an iterative correction scheme -- IKC that achieves better results than direct kernel estimation. We further propose an effective SR network architecture using spatial feature transform (SFT) layers to handle multiple blur kernels, named SFTMD. Extensive experiments on synthetic and real-world images show that the proposed IKC method with SFTMD can provide visually favorable SR results and the state-of-the-art performance in blind SR problem.

For agents

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

get_harvested_code_for_paper("1904.03377")
get_code_for_paper("1904.03377")
have("1904.03377")

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

curl https://syntology.ai/api/ran/1904.03377.json

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

[![Syntology run record](https://syntology.ai/api/ran/1904.03377.svg)](https://syntology.ai/paper/1904.03377)

Connect an agent — have() is free.