SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.11799 · CVPR · 2022

AP-BSN: Self-Supervised Denoising for Real-World Images via Asymmetric PD and Blind-Spot Network

Kyoung Lee, Sanghyun Son, Wooseok Lee

arXiv · PDF · Open in the Atlas

Code that ran

6 of 8 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 1 violated it and 1 has no contract verdict; 4 failures of our instrument; 2 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/2203.11799.json · badge: /api/ran/2203.11799.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
ucaszyp/steps community (classifier label)
classifier basis not recorded on the link
5 ran · 1 no recorded run
wooseoklee4/AP-BSN community
Papers with Code archive
1 ran · 1 no recorded run
FunctionStatusWhere it lives
DBSNl Ran
ran on a synthesized input · constructed an object; no result was computed
wooseoklee4/AP-BSN/src/model/APBSN.py
code served (permissive licence) · get_code("c1319ce8a90e6268")
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 an instance of its own class, DBSNl: the run constructed the object and did not call it, so no result was computed. 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
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    'in_ch': 3,
    'out_ch': 3,
    'base_ch': 128,
    'num_module': 9,
}
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 DBSNl — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a DBSNl output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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
disp_to_depth Ran
ran, violated the contract we drafted
ucaszyp/steps/components/layers.py
code served (permissive licence) · get_code("62287188376f0ba0")
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 tuple, ndim 4, 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 torch
import numpy as np

torch.manual_seed(0)

# Create a small disparity tensor
# Shape: (batch_size=2, height=4, width=3)
disp = torch.rand(2, 4, 3)

# Set min_depth and max_depth as scalars
min_depth = 0.1
max_depth = 100.0

ARGS = {
    "disp": disp,
    "min_depth": min_depth,
    "max_depth": max_depth,
}
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 tuple, ndim 4, dtype family float — a tuple output has no array shape of its own; none is stated
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_translation_matrix Ran
ran; our contract draft was wrong, not the code
ucaszyp/steps/components/layers.py
code served (permissive licence) · get_code("955112f5788539a8")
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, 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 translation vector with shape (batch_size=2, 3)
# The function expects a tensor with shape (N, 3) where N is batch size
translation_vector = torch.randn(2, 3)

ARGS = {
    "translation_vector": translation_vector
}
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, 4) — shape (2, 4, 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
resnet18_backbone Ran
ran; our contract draft was wrong, not the code
ucaszyp/steps/components/resnet_backbone.py
code served (permissive licence) · get_code("08cfd0df32f897ae")
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 ResNet. 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
import torch.nn as nn
from unittest.mock import patch, MagicMock

torch.manual_seed(0)

# Mock the model URLs and load function to avoid file I/O
def mock_load_pretrained_weights(name: str, map_location: str):
    # Return a mock state dict instead of loading from file
    model = nn.Linear(10, 10)
    return model.state_dict()

# Patch the _MODEL_URLS and load_pretrained_weights in the module
_MODEL_URLS = {
    'resnet18': '../Res_Models/resnet18-5c106cde.pth',
    'resnet34': '../Res_Models/resnet34-333f7ec4.pth',
    'resnet50': '../Res_Models/resnet50-19c8e357.pth'
}

ARGS = {
    'pre_trained': False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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
resnet34_backbone Ran
ran; our contract draft was wrong, not the code
ucaszyp/steps/components/resnet_backbone.py
code served (permissive licence) · get_code("d5082e6229312f27")
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 ResNet. 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
from torchvision.models import resnet34

torch.manual_seed(0)

ARGS = {
    'pre_trained': False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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
transformation_from_parameters Ran
ran; our contract draft was wrong, not the code
ucaszyp/steps/components/layers.py
code served (permissive licence) · get_code("cdc03d6bfc4d3a34")
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, 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)

# Small batch size of 2, axisangle vectors are Bx1x3
axisangle = torch.randn(2, 1, 3)

# Small batch size of 2, translation vectors are Bx3
translation = torch.randn(2, 3)

# Boolean parameter for inversion
invert = False

ARGS = {
    "axisangle": axisangle,
    "translation": translation,
    "invert": invert,
}
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, 4) — shape (2, 4, 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
APBSN Not yet run
unverified (harvested, no recorded run)
wooseoklee4/AP-BSN/src/model/APBSN.py
code served (permissive licence) · get_code("edad589bb83c337b")
How it ran

no invocation recorded.

load_pretrained_weights Not yet run
unverified (harvested, no recorded run)
ucaszyp/steps/components/resnet_backbone.py
code served (permissive licence) · get_code("41226517c1fbe4bf")
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, 6 are also present in other papers whose code we hold (6 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
disp_to_depth 18 other papers
6 dated earlier, 12 later
1806.01260 (2018-06)
Digging Into Self-Supervised Monocular Depth Estimation
1809.02627 (2018-09)
Unity: A General Platform for Intelligent Agents
1907.10326 (2019-07)
From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation
and 15 more not named here
transformation_from_parameters 17 other papers
6 dated earlier, 11 later
1809.02627 (2018-09)
Unity: A General Platform for Intelligent Agents
1907.10326 (2019-07)
From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation
2008.01484 (2020-08)
Learning Stereo from Single Images
and 14 more not named here
get_translation_matrix 14 other papers
6 dated earlier, 8 later
1809.02627 (2018-09)
Unity: A General Platform for Intelligent Agents
1907.10326 (2019-07)
From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation
2008.01484 (2020-08)
Learning Stereo from Single Images
and 11 more not named here
load_pretrained_weights 1 other paper
1 dated earlier
2108.03830 (2021-08)
Regularizing Nighttime Weirdness: Efficient Self-supervised Monocular Depth Estimation in the Dark
resnet18_backbone 1 other paper
1 dated earlier
2108.03830 (2021-08)
Regularizing Nighttime Weirdness: Efficient Self-supervised Monocular Depth Estimation in the Dark
resnet34_backbone 1 other paper
1 dated earlier
2108.03830 (2021-08)
Regularizing Nighttime Weirdness: Efficient Self-supervised Monocular Depth Estimation in the Dark

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

Blind-spot network (BSN) and its variants have made significant advances in self-supervised denoising. Nevertheless, they are still bound to synthetic noisy inputs due to less practical assumptions like pixel-wise independent noise. Hence, it is challenging to deal with spatially correlated real-world noise using self-supervised BSN. Recently, pixel-shuffle downsampling (PD) has been proposed to remove the spatial correlation of real-world noise. However, it is not trivial to integrate PD and BSN directly, which prevents the fully self-supervised denoising model on realworld images. We propose an Asymmetric PD (AP) to address this issue, which introduces different PD stride factors for training and inference. We systematically demonstrate that the proposed AP can resolve inherent trade-offs caused by specific PD stride factors and make BSN applicable to practical scenarios. To this end, we develop AP-BSN, a state-of-the-art self-supervised denoising method for realworld sRGB images. We further propose random-replacing refinement, which significantly improves the performance of our AP-BSN without any additional parameters. Extensive studies demonstrate that our method outperforms the other self-supervised and even unpaired denoising methods by a large margin, without using any additional knowledge, e.g., noise level, regarding the underlying unknown noise.

For agents

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

get_harvested_code_for_paper("2203.11799")
get_code_for_paper("2203.11799")
have("2203.11799")

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

curl https://syntology.ai/api/ran/2203.11799.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.11799.svg)](https://syntology.ai/paper/2203.11799)

Connect an agent — have() is free.