SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2201.13256 · 2022

Proximal Denoiser for Convergent Plug-and-Play Optimization with Nonconvex Regularization

arXiv · PDF · Open in the Atlas

Code that ran

7 of 9 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; 1 honoured the contract we drafted, 0 violated it and 6 have no contract verdict; 0 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/2201.13256.json · badge: /api/ran/2201.13256.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
samuro95/prox-pnp canonical (classifier label)
classifier basis not recorded on the link
7 ran · 2 no recorded run
FunctionStatusWhere it lives
blockproc Ran
ran on a synthesized input
samuro95/prox-pnp/PnP_restoration/utils/utils_sr.py
code served (permissive licence) · get_code("a5f896944a03d905")
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 (8, 6) 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

# blockproc processes an image by dividing it into blocks and applying a function to each block
# Parameters:
# - im: a numpy array (image)
# - blocksize: a tuple/list of (height, width) for block dimensions
# - fun: a function that takes a block and returns a processed block

# Create a small image as input
im = np.random.rand(8, 6).astype(np.float32)

# Define block size
blocksize = (4, 3)

# Define a function that processes each block
# The function receives a numpy array block and should return a processed block
def process_block(block):
    # Simple operation: compute mean of the block
    return np.full_like(block, block.mean())

ARGS = {
    "im": im,
    "blocksize": blocksize,
    "fun": process_block
}
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 (8, 6) — shape (8, 6) 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
fun_reshape Ran
ran on a synthesized input
samuro95/prox-pnp/PnP_restoration/utils/utils_sr.py
code served (permissive licence) · get_code("a94cdf48560711e9")
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 (12, 1, 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 numpy as np

# Create a small test array with shape (3, 4, 5)
# This will be reshaped to (-1, 1, 5) using Fortran order
a = np.arange(60).reshape(3, 4, 5)

ARGS = {
    'a': a
}
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 3, dtype family int, shape (12, 1, 5) — shape (12, 1, 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
get_rho_sigma Ran
ran on a synthesized input
samuro95/prox-pnp/PnP_restoration/utils/utils_deblur.py
code served (permissive licence) · get_code("9fe27315fe97ae9b")
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 2, 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

ARGS = {
    "sigma": 2.55 / 255,
    "iter_num": 15
}
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 tuple, ndim 2, 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
imread_uint Ran
ran, honoured the contract we drafted
samuro95/prox-pnp/PnP_restoration/utils/utils_restoration.py
code served (permissive licence) · get_code("72d98b47ea73bd56")
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 (10, 10, 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 cv2
import tempfile
import os

# Create a temporary image file for testing
temp_dir = tempfile.mkdtemp()
temp_image_path = os.path.join(temp_dir, "test_image.png")

# Create a simple RGB image and save it
rgb_image = np.random.randint(0, 256, (10, 10, 3), dtype=np.uint8)
cv2.imwrite(temp_image_path, cv2.cvtColor(rgb_image, cv2.COLOR_RGB2BGR))

ARGS = {
    "path": temp_image_path,
    "n_channels": 3
}
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 ndarray, ndim 3, dtype family int, shape (10, 10, 3) — shape (10, 10, 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
modcrop Ran
ran on a synthesized input
samuro95/prox-pnp/PnP_restoration/utils/utils_restoration.py
code served (permissive licence) · get_code("8c6468052b1b52eb")
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 float, shape (10, 12, 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

# Test with a 2D grayscale image
img_2d = np.random.rand(10, 12)

# Test with a 3D RGB image
img_3d = np.random.rand(10, 12, 3)

# Scale factor that divides evenly into some dimensions
scale = 2

ARGS = {
    "img_in": img_3d,
    "scale": scale
}
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 3, dtype family float, shape (10, 12, 3) — shape (10, 12, 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
otf2psf Ran
ran on a synthesized input
samuro95/prox-pnp/PnP_restoration/utils/utils_deblur.py
code served (permissive licence) · get_code("5cb805290cf1d779")
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 (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 numpy as np

# Create a small OTF (Optical Transfer Function) array
# OTF is typically a complex-valued array
# Using shape (4, 3) for distinctness
otf = np.random.randn(4, 3) + 1j * np.random.randn(4, 3)

# outsize can be None or a tuple/list specifying output dimensions
# Making it smaller than otf to test the cropping logic
outsize = (2, 2)

ARGS = {
    "otf": otf,
    "outsize": outsize,
}
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 (2, 2) — shape (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
randomCrop Ran
ran on a synthesized input
samuro95/prox-pnp/PnP_restoration/utils/utils_restoration.py
code served (permissive licence) · get_code("a05624ca6ad6870e")
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 int; 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 random
import numpy as np
import torch

torch.manual_seed(0)
random.seed(0)

# Create two sample images as numpy arrays
# Images need to be at least as large as the crop dimensions
# Using distinct dimensions: height=6, width=8 for images
# This allows cropping to height=4, width=5
img1 = np.random.randint(0, 256, size=(6, 8, 3), dtype=np.uint8)
img2 = np.random.randint(0, 256, size=(6, 8, 3), dtype=np.uint8)

width = 5
height = 4

ARGS = {
    "img1": img1,
    "img2": img2,
    "width": width,
    "height": height,
}
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 int — 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
fun_mul Not yet run
unverified (harvested, no recorded run)
samuro95/prox-pnp/PnP_restoration/utils/utils_sr.py
code served (permissive licence) · get_code("fb5d5779350ffe96")
How it ran

no invocation recorded.

get_uperleft_denominator Not yet run
unverified (harvested, no recorded run)
samuro95/prox-pnp/PnP_restoration/utils/utils_deblur.py
code served (permissive licence) · get_code("df2f94719784027b")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 8 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
imread_uint 5 other papers
2 dated earlier, 3 later
2009.11551 (2020-09)
Residual Feature Distillation Network for Lightweight Image Super-Resolution
2110.03220 (2021-10)
Gradient Step Denoiser for convergent Plug-and-Play
aaai_25291 (2023 (year only))
Robust Image Denoising of No-Flash Images Guided by Consistent Flash Images
and 2 more not named here

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

Plug-and-Play (PnP) methods solve ill-posed inverse problems through iterative proximal algorithms by replacing a proximal operator by a denoising operation. When applied with deep neural network denoisers, these methods have shown state-of-the-art visual performance for image restoration problems. However, their theoretical convergence analysis is still incomplete. Most of the existing convergence results consider nonexpansive denoisers, which is non-realistic, or limit their analysis to strongly convex data-fidelity terms in the inverse problem to solve. Recently, it was proposed to train the denoiser as a gradient descent step on a functional parameterized by a deep neural network. Using such a denoiser guarantees the convergence of the PnP version of the Half-Quadratic-Splitting (PnP-HQS) iterative algorithm. In this paper, we show that this gradient denoiser can actually correspond to the proximal operator of another scalar function. Given this new result, we exploit the convergence theory of proximal algorithms in the nonconvex setting to obtain convergence results for PnP-PGD (Proximal Gradient Descent) and PnP-ADMM (Alternating Direction Method of Multipliers). When built on top of a smooth gradient denoiser, we show that PnP-PGD and PnP-ADMM are convergent and target stationary points of an explicit functional. These convergence results are confirmed with numerical experiments on deblurring, super-resolution and inpainting.

For agents

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

get_harvested_code_for_paper("2201.13256")
get_code_for_paper("2201.13256")
have("2201.13256")

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

curl https://syntology.ai/api/ran/2201.13256.json

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

[![Syntology run record](https://syntology.ai/api/ran/2201.13256.svg)](https://syntology.ai/paper/2201.13256)

Connect an agent — have() is free.