SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1611.06403 · 2016

Deep Outdoor Illumination Estimation

arXiv · PDF · Open in the Atlas

Code that ran

7 of 12 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 5 have no contract verdict; 2 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/1611.06403.json · badge: /api/ran/1611.06403.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
CyxFTS/Scenne-illumination-estimation-from-single-image community (classifier label)
classifier basis not recorded on the link
7 ran · 5 no recorded run
FunctionStatusWhere it lives
conv3x3 Ran
ran; our contract draft was wrong, not the code
CyxFTS/Scenne-illumination-estimation-from-single-image/NeuralNetwork/loader.py
pointer only (licence: MIT); the stored copy get_code serves, from lixiaotong97/DSU, is pointer only (licence: NONE) · get_code("fac5364e2f53c6db")
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 lixiaotong97/DSU, and GitHub detected no licence in that repository when it was checked. 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.

conv_bn Ran
ran; our contract draft was wrong, not the code
CyxFTS/Scenne-illumination-estimation-from-single-image/NeuralNetwork/loader.py
code served (permissive licence) · get_code("e087cbfa1e53486d")
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) and returned Sequential. 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 = {
    "inp": 3,
    "oup": 16,
    "stride": 1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
conv_bn_elu Ran
ran on a synthesized input
CyxFTS/Scenne-illumination-estimation-from-single-image/NeuralNetwork/loader.py
code served (permissive licence) · get_code("b375695898ddde78")
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 Sequential. 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_": 3,
    "out_": 16,
    "kernel_size": 3,
    "stride": 1,
    "padding": True,
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
make360Datalist Ran
ran on a synthesized input
CyxFTS/Scenne-illumination-estimation-from-single-image/NeuralNetwork/generate_data.py
code served (permissive licence) · get_code("10fecc75aa6014ef")
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 csv
import tempfile
import os
import numpy as np

# Create a temporary CSV file with the expected columns
temp_dir = tempfile.mkdtemp()
csv_file = os.path.join(temp_dir, "test_360_data.csv")

with open(csv_file, 'w', newline='') as f:
    writer = csv.DictWriter(f, fieldnames=['PanoID', 'theta', 'phi', 'turbidity', 'exposure'])
    writer.writeheader()
    writer.writerow({
        'PanoID': 'pano_001',
        'theta': '45.5',
        'phi': '120.3',
        'turbidity': '1.5',
        'exposure': '0.8'
    })
    writer.writerow({
        'PanoID': 'pano_002',
        'theta': '30.0',
        'phi': '200.5',
        'turbidity': '2.1',
        'exposure': '1.2'
    })

ARGS = {
    'fname': csv_file
}
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 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
make360Datalist Ran
ran on a synthesized input
CyxFTS/Scenne-illumination-estimation-from-single-image/NeuralNetwork/write.py
code served (permissive licence) · get_code("a4268cf03ecfc8d7")
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 numpy as np
import csv
import tempfile
import os

# Create a temporary CSV file with the required columns
temp_dir = tempfile.mkdtemp()
csv_file = os.path.join(temp_dir, 'test_data.csv')

with open(csv_file, 'w', newline='') as f:
    writer = csv.DictWriter(f, fieldnames=['filepath', 'turbidity', 'exposure', 'elevation', 'fov', 'theta', 'phi'])
    writer.writeheader()
    writer.writerow({
        'filepath': '/path/to/pano1.jpg',
        'turbidity': '1.5',
        'exposure': '0.8',
        'elevation': '45',
        'fov': '120',
        'theta': '0.5',
        'phi': '1.2'
    })
    writer.writerow({
        'filepath': '/path/to/pano2.jpg',
        'turbidity': '2.0',
        'exposure': '1.0',
        'elevation': '60',
        'fov': '110',
        'theta': '1.5',
        'phi': '2.1'
    })

ARGS = {
    'fname': csv_file
}
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 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
pythonize_assimp Ran
ran on a synthesized input
CyxFTS/Scenne-illumination-estimation-from-single-image/GLEngine/api/assimp/port/PyAssimp/pyassimp/core.py
code served (permissive licence) · get_code("c0695ba0f66b26b8")
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 numpy as np

class MockNode:
    def __init__(self, name, transformation=None, children=None):
        self.name = name
        self.transformation = transformation if transformation is not None else np.eye(4)
        self.children = children if children is not None else []

class MockMesh:
    def __init__(self, mesh_id):
        self.mesh_id = mesh_id

class MockObject:
    def __init__(self, name):
        self.name = name

class MockScene:
    def __init__(self):
        self.meshes = [MockMesh(0), MockMesh(1), MockMesh(2)]
        child_node = MockNode("child_node", np.eye(4))
        self.rootnode = MockNode("root", np.eye(4), children=[child_node])

obj_for_mesh = [0, 1]
obj_for_transformation = MockObject("child_node")
scene = MockScene()

ARGS = {
    "type": "MESH",
    "obj": obj_for_mesh,
    "scene": scene
}
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 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
world2sphere Ran
ran on a synthesized input
CyxFTS/Scenne-illumination-estimation-from-single-image/NeuralNetwork/libs/projections.py
code served (permissive licence) · get_code("9d8fd6adf8edacc8")
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 1, dtype family float, shape (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

ARGS = {
    'x': 0.5,
    'y': 0.3,
    'z': 0.8,
}
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 1, dtype family float, shape (2,) — shape (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
make360Datalist Not yet run
unverified (harvested, no recorded run)
CyxFTS/Scenne-illumination-estimation-from-single-image/NeuralNetwork/getdata.py
code served (permissive licence) · get_code("d5eac2f877c48381")
How it ran

no invocation recorded.

make_dot Not yet run
unverified (harvested, no recorded run)
CyxFTS/Scenne-illumination-estimation-from-single-image/NeuralNetwork/visualize_net.py
code served (permissive licence) · get_code("0311b99405df4c9d")
How it ran

no invocation recorded.

make_tuple Not yet run
unverified (harvested, no recorded run)
CyxFTS/Scenne-illumination-estimation-from-single-image/GLEngine/api/assimp/port/PyAssimp/pyassimp/core.py
code served (permissive licence) · get_code("c2ed163e54d9cf14")
How it ran

no invocation recorded.

sphere2uv Not yet run
unverified (harvested, no recorded run)
CyxFTS/Scenne-illumination-estimation-from-single-image/NeuralNetwork/libs/projections.py
code served (permissive licence) · get_code("9ed2a4c67c733ab8")
How it ran

no invocation recorded.

sphere2world Not yet run
unverified (harvested, no recorded run)
CyxFTS/Scenne-illumination-estimation-from-single-image/NeuralNetwork/libs/projections.py
code served (permissive licence) · get_code("1797e21bbaac38d3")
How it ran

no invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 2 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 2 later) and 9 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
conv3x3 686 other papers
17 dated earlier, 1 the same month, 668 later · 31 only as an assembly brick
1406.2661 (2014-06)
Generative Adversarial Networks
1409.0575 (2014-09)
ImageNet Large Scale Visual Recognition Challenge
1412.6572 (2014-12)
Explaining and Harnessing Adversarial Examples
and 683 more not named here
conv_bn 18 other papers
18 later · 1 only as an assembly brick
1703.07402 (2017-03)
Simple Online and Realtime Tracking with a Deep Association Metric
1801.04381 (2018-01)
MobileNetV2: Inverted Residuals and Linear Bottlenecks
1811.08383 (2018-11)
TSM: Temporal Shift Module for Efficient Video Understanding
and 15 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

We present a CNN-based technique to estimate high-dynamic range outdoor illumination from a single low dynamic range image. To train the CNN, we leverage a large dataset of outdoor panoramas. We fit a low-dimensional physically-based outdoor illumination model to the skies in these panoramas giving us a compact set of parameters (including sun position, atmospheric conditions, and camera parameters). We extract limited field-of-view images from the panoramas, and train a CNN with this large set of input image--output lighting parameter pairs. Given a test image, this network can be used to infer illumination parameters that can, in turn, be used to reconstruct an outdoor illumination environment map. We demonstrate that our approach allows the recovery of plausible illumination conditions and enables photorealistic virtual object insertion from a single image. An extensive evaluation on both the panorama dataset and captured HDR environment maps shows that our technique significantly outperforms previous solutions to this problem.

For agents

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

get_harvested_code_for_paper("1611.06403")
get_code_for_paper("1611.06403")
have("1611.06403")

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

curl https://syntology.ai/api/ran/1611.06403.json

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

[![Syntology run record](https://syntology.ai/api/ran/1611.06403.svg)](https://syntology.ai/paper/1611.06403)

Connect an agent — have() is free.