SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2304.01598 · 2023

MM-BSN: Self-Supervised Image Denoising for Real-World with Multi-Mask based on Blind-Spot Network

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 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 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/2304.01598.json · badge: /api/ran/2304.01598.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
dannie125/mm-bsn canonical (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
FunctionStatusWhere it lives
get_patch Ran
ran on a synthesized input
dannie125/mm-bsn/DataDeal/DatasetBase.py
code served (permissive licence) · get_code("f2f41ffe55dce700")
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 dict. 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 numpy as np

# Set seed for reproducibility
np.random.seed(0)

# Create sample data dictionary with 'clean' and 'real_noisy' keys
# Shape format: (channels, height, width)
# Make sure dimensions are large enough to allow cropping
batch_size = 2
channels = 3
height = 32
width = 40

clean_data = np.random.rand(batch_size, height, width).astype(np.float32)
real_noisy_data = np.random.rand(batch_size, height, width).astype(np.float32)

data = {
    'clean': clean_data,
    'real_noisy': real_noisy_data
}

# Crop size as (width, height)
crop_size = (16, 20)

# Define ARGS
ARGS = {
    'crop_size': crop_size,
    'data': data,
    'rnd': 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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
is_image_tensor Ran
ran on a synthesized input
dannie125/mm-bsn/DataDeal/DatasetBase.py
code served (permissive licence) · get_code("1ca14dc53dd7f22e")
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 bool, ndim 0, dtype family float, shape () 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)

# Test case 1: Valid batched image tensor (4D)
batched_image = torch.randn(2, 3, 4, 5)

# Test case 2: Valid single image tensor (3D)
single_image = torch.randn(3, 4, 5)

# Test case 3: Invalid boolean tensor (should return False)
bool_tensor = torch.ones(2, 3, 4, dtype=torch.bool)

# Test case 4: Invalid 2D tensor (should return False)
tensor_2d = torch.randn(4, 5)

# Test case 5: Invalid 5D tensor (should return False)
tensor_5d = torch.randn(2, 3, 4, 5, 6)

# Test case 6: Non-tensor input (should return False)
non_tensor = [1, 2, 3]

# We'll test with the batched image tensor
ARGS = {
    "x": batched_image
}
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 bool, ndim 0, dtype family float, shape () — shape () 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
set_dataloader Ran
ran on a synthesized input
dannie125/mm-bsn/DataDeal/DatasetBase.py
code served (permissive licence) · get_code("4057299f4c36663b")
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 dict. 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 torch.utils.data import Dataset, DataLoader

torch.manual_seed(0)

class DummyDataset(Dataset):
    def __init__(self, dataset_name):
        self.dataset_name = dataset_name
        self.data = torch.randn(10, 4)
        self.labels = torch.randint(0, 2, (10,))
    
    def __call__(self, **kwargs):
        return self
    
    def __len__(self):
        return len(self.data)
    
    def __getitem__(self, idx):
        return self.data[idx], self.labels[idx]

dataset_cfg = {
    'dataset': {
        'train': 'train_dataset',
        'val': 'val_dataset'
    },
    'train_args': {},
    'val_args': {}
}

ARGS = {
    'dataset_class': DummyDataset,
    'dataset_cfg': dataset_cfg,
    'batch_size': 2,
    'shuffle': True,
    'num_workers': 0
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 3 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.

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

Recent advances in deep learning have been pushing image denoising techniques to a new level. In self-supervised image denoising, blind-spot network (BSN) is one of the most common methods. However, most of the existing BSN algorithms use a dot-based central mask, which is recognized as inefficient for images with large-scale spatially correlated noise. In this paper, we give the definition of large-noise and propose a multi-mask strategy using multiple convolutional kernels masked in different shapes to further break the noise spatial correlation. Furthermore, we propose a novel self-supervised image denoising method that combines the multi-mask strategy with BSN (MM-BSN). We show that different masks can cause significant performance differences, and the proposed MM-BSN can efficiently fuse the features extracted by multi-masked layers, while recovering the texture structures destroyed by multi-masking and information transmission. Our MM-BSN can be used to address the problem of large-noise denoising, which cannot be efficiently handled by other BSN methods. Extensive experiments on public real-world datasets demonstrate that the proposed MM-BSN achieves state-of-the-art performance among self-supervised and even unpaired image denoising methods for sRGB images denoising, without any labelling effort or prior knowledge. Code can be found in https://github.com/dannie125/MM-BSN.

For agents

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

get_harvested_code_for_paper("2304.01598")
get_code_for_paper("2304.01598")
have("2304.01598")

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

curl https://syntology.ai/api/ran/2304.01598.json

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

[![Syntology run record](https://syntology.ai/api/ran/2304.01598.svg)](https://syntology.ai/paper/2304.01598)

Connect an agent — have() is free.