SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1908.08628 · 2019

Shadow Removal via Shadow Image Decomposition

arXiv · PDF · Open in the Atlas

Code that ran

8 of 11 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 7 have no contract verdict; 1 failure of our instrument; 3 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/1908.08628.json · badge: /api/ran/1908.08628.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
lmhieu612/SID canonical (classifier label)
classifier basis: census
0 ran · 3 no recorded run
naoto0804/SynShadow community (classifier label)
classifier basis not recorded on the link
8 ran · 0 no recorded run
FunctionStatusWhere it lives
apply_tone_curve Ran
ran on a synthesized input
naoto0804/SynShadow/src/util/illum_affine_model.py
code served (permissive licence) · get_code("7b6ac2089343d3c3")
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, 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 torch

torch.manual_seed(0)

# Create a small 3D image tensor [C, H, W]
# C=3 for RGB, H=4, W=5 for distinct dimensions
image = torch.rand(3, 4, 5)

# Define gain tuple - one value per color channel
gain = (0.5, 0.5, 0.5)

# Define is_rgb flag
is_rgb = True

ARGS = {
    "image": image,
    "gain": gain,
    "is_rgb": is_rgb,
}
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 (3, 4, 5) — shape (3, 4, 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
copyconf Ran
ran on a synthesized input
naoto0804/SynShadow/src/util/util.py
pointer only (licence: MIT); the stored copy get_code serves, from shinde-Pratik/Image-Restoration, is pointer only (licence: MIT) · get_code("700b6c26b9f820a8")
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 shinde-Pratik/Image-Restoration, and MIT, as GitHub detects it on that repository, is in the permissive set, but a licence decision keeps the body a pointer: its licence file names an outside party, so it may cover vendored code rather than the repository owner's files (recorded as pointer:licence_names_third_party_corporation). 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.

find_image Ran
ran on a synthesized input
naoto0804/SynShadow/src/util/image.py
code served (permissive licence) · get_code("063e4397662f061e")
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 PosixPath. 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.

from pathlib import Path
import tempfile
import os

# Create a temporary directory with test image files
temp_dir = tempfile.mkdtemp()

# Create a test image file with .png extension
test_image_path = Path(temp_dir) / "test_image.png"
test_image_path.touch()

# Test case 1: path that exists as-is
existing_path = test_image_path

# Test case 2: path that doesn't exist but alternative extension does
non_existing_base = Path(temp_dir) / "another_image"
alternative_image = non_existing_base.with_suffix(".jpg")
alternative_image.touch()

ARGS = {
    "path": existing_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type PosixPath — a PosixPath output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a PosixPath 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
load Ran
ran on a synthesized input
naoto0804/SynShadow/src/util/image.py
code served (permissive licence) · get_code("5a112feba8f53b0c")
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 (6, 8, 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.

from pathlib import Path
from PIL import Image
import numpy as np
import tempfile
import os

# Create a temporary directory with a test image
temp_dir = tempfile.mkdtemp()
test_image_path = Path(temp_dir) / "test_image.png"

# Create a small test image
img = Image.new('RGB', (10, 10), color='red')
img.save(test_image_path)

# Define arguments for the load function
ARGS = {
    'path': test_image_path.with_suffix(''),  # path without suffix, will be found with .png
    'size': (8, 6)  # tuple of (width, height) for resize
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, 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 (6, 8, 3) — shape (6, 8, 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
load_obj Ran
ran; our contract draft was wrong, not the code
naoto0804/SynShadow/src/util/util.py
pointer only (licence: MIT); the stored copy get_code serves, from shinde-Pratik/Image-Restoration, is pointer only (licence: MIT) · get_code("30d56fdfbf93d0d3")
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 shinde-Pratik/Image-Restoration, and MIT, as GitHub detects it on that repository, is in the permissive set, but a licence decision keeps the body a pointer: its licence file names an outside party, so it may cover vendored code rather than the repository owner's files (recorded as pointer:licence_names_third_party_corporation). 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.

rgb_to_srgb Ran
ran on a synthesized input
naoto0804/SynShadow/src/util/illum_affine_model.py
code served (permissive licence) · get_code("c1ebd10caa104c75")
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 (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 small FloatTensor with values in the range [0, 1]
# to test the rgb_to_srgb function
value = torch.tensor([
    [0.0, 0.001, 0.0031308, 0.5],
    [0.7, 0.9, 1.0, 0.002]
], dtype=torch.float32)

ARGS = {
    "value": value
}
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 2, dtype family float, shape (2, 4) — shape (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
srgb_to_rgb Ran
ran on a synthesized input
naoto0804/SynShadow/src/util/illum_affine_model.py
code served (permissive licence) · get_code("ea2359b6d27138f3")
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 (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)

# The function expects a FloatTensor with values in sRGB color space (typically 0-1 range)
# It performs conditional in-place operations on the tensor
value = torch.tensor([
    [0.02, 0.05, 0.5, 0.9],
    [0.04045, 0.1, 0.3, 1.0]
], dtype=torch.float32)

ARGS = {
    "value": value
}
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 2, dtype family float, shape (2, 4) — shape (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
tile_images Ran
ran on a synthesized input
naoto0804/SynShadow/src/util/util.py
code served (permissive licence) · get_code("3e5e64c86e05a9f1")
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 (8, 12, 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 batch of images with distinct dimensions
# Shape: (num_images, height, width, channels)
# Using 5 images of size 4x3 with 2 channels each
np.random.seed(0)
imgs = np.random.randint(0, 256, size=(5, 4, 3, 2), dtype=np.uint8)

ARGS = {
    "imgs": imgs,
    "picturesPerRow": 4,
}
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 (8, 12, 2) — shape (8, 12, 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
im_darken Not yet run
unverified (harvested, no recorded run)
lmhieu612/SID/data_processing/dataset_augmentation.py
code served (permissive licence) · get_code("16bd26484cba3e49")
How it ran

no invocation recorded.

im_relit Not yet run
unverified (harvested, no recorded run)
lmhieu612/SID/data_processing/compute_params.py
code served (permissive licence) · get_code("c0d7139178892d99")
How it ran

no invocation recorded.

relit Not yet run
unverified (harvested, no recorded run)
lmhieu612/SID/data_processing/compute_params.py
code served (permissive licence) · get_code("d61e18f527623b40")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 4 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 4 later) and 7 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
load_obj 3 other papers
3 later
2004.09484 (2020-04)
Bringing Old Photos Back to Life
2007.06286 (2020-07)
Beyond Graph Neural Networks with Lifted Relational Neural Networks
2207.05202 (2022-07)
The Cosmic Graph: Optimal Information Extraction from Large-Scale Structure using Catalogues
copyconf 1 other paper
1 later
2004.09484 (2020-04)
Bringing Old Photos Back to Life
im_relit 1 other paper
1 later
2104.10338 (2021-04)
Shadow Generation for Composite Image in Real-world Scenes
relit 1 other paper
1 later
2104.10338 (2021-04)
Shadow Generation for Composite Image in Real-world Scenes

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

We propose a novel deep learning method for shadow removal. Inspired by physical models of shadow formation, we use a linear illumination transformation to model the shadow effects in the image that allows the shadow image to be expressed as a combination of the shadow-free image, the shadow parameters, and a matte layer. We use two deep networks, namely SP-Net and M-Net, to predict the shadow parameters and the shadow matte respectively. This system allows us to remove the shadow effects on the images. We train and test our framework on the most challenging shadow removal dataset (ISTD). Compared to the state-of-the-art method, our model achieves a 40% error reduction in terms of root mean square error (RMSE) for the shadow area, reducing RMSE from 13.3 to 7.9. Moreover, we create an augmented ISTD dataset based on an image decomposition system by modifying the shadow parameters to generate new synthetic shadow images. Training our model on this new augmented ISTD dataset further lowers the RMSE on the shadow area to 7.4.

For agents

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

get_harvested_code_for_paper("1908.08628")
get_code_for_paper("1908.08628")
have("1908.08628")

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

curl https://syntology.ai/api/ran/1908.08628.json

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

[![Syntology run record](https://syntology.ai/api/ran/1908.08628.svg)](https://syntology.ai/paper/1908.08628)

Connect an agent — have() is free.