SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.01628 · 2020

HDR-GAN: HDR Image Reconstruction from Multi-Exposed LDR Images with Large Motions

arXiv · PDF · Open in the Atlas

Code that ran

6 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 6 have no contract verdict; 0 failures of our instrument; 5 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/2007.01628.json · badge: /api/ran/2007.01628.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
nonu116/HDR-GAN canonical (classifier label)
classifier basis: census
6 ran · 5 no recorded run
FunctionStatusWhere it lives
hdr2ldr Ran
ran on a synthesized input
nonu116/HDR-GAN/hdr_utils.py
code served (permissive licence) · get_code("a27218cd5f05f289")
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 EagerTensor, 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 tensorflow as tf
import numpy as np

GAMMA = 2.2

def hdr2ldr(hdr, expo):
    return tf.clip_by_value((hdr + 1) / 2.0 * expo, 0, 1) ** (1 / GAMMA) * 2.0 - 1

# Create small test tensors
hdr_tensor = tf.constant(np.random.randn(2, 4).astype(np.float32), dtype=tf.float32)
expo_tensor = tf.constant(1.5, dtype=tf.float32)

ARGS = {
    "hdr": hdr_tensor,
    "expo": expo_tensor,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, 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
ldr2hdr Ran
ran on a synthesized input
nonu116/HDR-GAN/hdr_utils.py
code served (permissive licence) · get_code("477b1bfcf3242f80")
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
import numpy as np

torch.manual_seed(0)

# The function ldr2hdr takes two parameters:
# - ldr: appears to be a tensor (used with arithmetic operations)
# - expo: appears to be a scalar or tensor (used in division)

# Create a small LDR (Low Dynamic Range) tensor
ldr = torch.randn(2, 4)

# Create a small exposure value (scalar tensor or float)
expo = torch.tensor(1.5)

ARGS = {
    "ldr": ldr,
    "expo": expo
}
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 (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
make_flist Ran
ran on a synthesized input
nonu116/HDR-GAN/data.py
code served (permissive licence) · get_code("d64d2648299df498")
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 list, ndim 1, 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 tempfile
import os

# Create a temporary file with test data
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, "test_flist.txt")

# Write test content to the file
with open(temp_file, 'w') as fw:
    fw.write("file1.txt\n")
    fw.write("file2.jpg\n")
    fw.write("x\n")  # This will be filtered out (len <= 2)
    fw.write("file3.png\n")
    fw.write("\n")  # This will be filtered out (len <= 2)
    fw.write("file4.mp4\n")

ARGS = {
    "file_name": temp_file
}
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 list, ndim 1, dtype family float — a list 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
read_hdr Ran
ran on a synthesized input
nonu116/HDR-GAN/hdr_utils.py
code served (permissive licence) · get_code("ac0e3e6e1114c511")
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 (4, 3, 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 cv2
import numpy as np
import tempfile
import os

# Create a temporary HDR image file for testing
# We'll create a simple image and save it
temp_dir = tempfile.mkdtemp()
hdr_path = os.path.join(temp_dir, "test.hdr")

# Create a simple 3-channel image (BGR format for OpenCV)
# Use uint8 values that when read will be converted to float32
test_image = np.random.randint(0, 256, (4, 3, 3), dtype=np.uint8)

# Write as PNG (OpenCV will handle it)
cv2.imwrite(hdr_path, test_image)

ARGS = {
    "hdr_path": hdr_path
}
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 float, shape (4, 3, 3) — shape (4, 3, 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
swish Ran
ran on a synthesized input
nonu116/HDR-GAN/model/ops.py
code served (permissive licence) · get_code("0dd04ca12c7f9c98")
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 EagerTensor, 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 tensorflow as tf
import numpy as np

# Create a small TensorFlow tensor for testing
input_tensor = tf.constant([[1.0, 2.0, 3.0, 4.0],
                             [5.0, 6.0, 7.0, 8.0]], dtype=tf.float32)

ARGS = {
    "input_tensor": input_tensor
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 2, dtype family float — no output shape is stated: observe_signature.py recorded SymbolicTensor ndim 2, 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
wrap_tf_variable_scope Ran
ran on a synthesized input
nonu116/HDR-GAN/tensorkit/annotation.py
code served (permissive licence) · get_code("e622e141fedff9be")
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 function. 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 tensorflow as tf
from functools import wraps

def wrap_tf_variable_scope(name):
    def _deco(func):
        @wraps(func)
        def _d(*args, **kwargs):
            with tf.variable_scope(name):
                return func(*args, **kwargs)
        return _d
    return _deco

def sample_function(x):
    return x * 2

ARGS = {
    "name": "my_variable_scope"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
args Not yet run
unverified (harvested, no recorded run)
nonu116/HDR-GAN/train_unetpps.py
code served (permissive licence) · get_code("ff141828ea9a5534")
How it ran

no invocation recorded.

merge_net Not yet run
unverified (harvested, no recorded run)
nonu116/HDR-GAN/model/unetpps.py
code served (permissive licence) · get_code("6e30004ddbc4fc53")
How it ran

no invocation recorded.

optimize_op Not yet run
unverified (harvested, no recorded run)
nonu116/HDR-GAN/utils.py
code served (permissive licence) · get_code("6c89d048ab5258e0")
How it ran

no invocation recorded.

spectral_norm Not yet run
unverified (harvested, no recorded run)
nonu116/HDR-GAN/model/ops.py
code served (permissive licence) · get_code("c170561e8e9f4daf")
How it ran

no invocation recorded.

weight_norm Not yet run
unverified (harvested, no recorded run)
nonu116/HDR-GAN/model/ops.py
code served (permissive licence) · get_code("eee2c043144fd19a")
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, 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 11 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

Synthesizing high dynamic range (HDR) images from multiple low-dynamic range (LDR) exposures in dynamic scenes is challenging. There are two major problems caused by the large motions of foreground objects. One is the severe misalignment among the LDR images. The other is the missing content due to the over-/under-saturated regions caused by the moving objects, which may not be easily compensated for by the multiple LDR exposures. Thus, it requires the HDR generation model to be able to properly fuse the LDR images and restore the missing details without introducing artifacts. To address these two problems, we propose in this paper a novel GAN-based model, HDR-GAN, for synthesizing HDR images from multi-exposed LDR images. To our best knowledge, this work is the first GAN-based approach for fusing multi-exposed LDR images for HDR reconstruction. By incorporating adversarial learning, our method is able to produce faithful information in the regions with missing content. In addition, we also propose a novel generator network, with a reference-based residual merging block for aligning large object motions in the feature domain, and a deep HDR supervision scheme for eliminating artifacts of the reconstructed HDR images. Experimental results demonstrate that our model achieves state-of-the-art reconstruction performance over the prior HDR methods on diverse scenes.

For agents

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

get_harvested_code_for_paper("2007.01628")
get_code_for_paper("2007.01628")
have("2007.01628")

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

curl https://syntology.ai/api/ran/2007.01628.json

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

[![Syntology run record](https://syntology.ai/api/ran/2007.01628.svg)](https://syntology.ai/paper/2007.01628)

Connect an agent — have() is free.