SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2201.02279 · CVPR · 2022

De-rendering 3D Objects in the Wild

Christian Rupprecht, Shangzhe Wu, Felix Wimbauer

arXiv · PDF · Open in the Atlas

Code that ran

9 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 9 have no contract verdict; 0 failures of our instrument; 2 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/2201.02279.json · badge: /api/ran/2201.02279.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
brummi/derender3d canonical (classifier label)
classifier basis not recorded on the link
9 ran · 2 no recorded run
FunctionStatusWhere it lives
compute_shadow Ran
ran on a synthesized input
brummi/derender3d/derender3d/image_formation_models.py
code served (permissive licence) · get_code("bfae1c7ebcfb4d8c")
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 4, dtype family float, shape (2, 1, 4, 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 math

torch.manual_seed(0)

# depth: tensor with shape (batch_size, 1, image_size, image_size)
# The function expects depth to have at least 4 dimensions with last dimension as image_size
depth = torch.randn(2, 1, 4, 4)

# light_dir: tensor with shape (batch_size, 3)
# The function reshapes it to (-1, 3, 1, 1) for broadcasting
light_dir = torch.randn(2, 3)

# fov: field of view angle in degrees (default 10)
fov = 10

ARGS = {
    "depth": depth,
    "light_dir": light_dir,
    "fov": fov
}
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 4, dtype family float, shape (2, 1, 4, 4) — shape (2, 1, 4, 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
from_gamma_space Ran
ran on a synthesized input
brummi/derender3d/derender3d/image_formation_models.py
code served (permissive licence) · get_code("be1c7090959b37e8")
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 4, dtype family float, shape (2, 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)

# The function takes an image tensor and applies inverse gamma correction
# It clamps the tensor to a minimum of EPS and raises it to the power of 1/GAMMA
# The function expects a tensor with .clamp() and ** operator support

img = torch.rand(2, 3, 4, 5)  # Small batch of images: (batch=2, channels=3, height=4, width=5)

ARGS = {
    "img": img
}
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 4, dtype family float, shape (2, 3, 4, 5) — shape (2, 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
get_set_path Ran
ran on a synthesized input
brummi/derender3d/derender3d/dataloaders.py
code served (permissive licence) · get_code("4dd724fba0f40265")
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 str. 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 os
import tempfile
import shutil

# Create temporary directories for testing
temp_base = tempfile.mkdtemp()
temp_set = tempfile.mkdtemp(dir=temp_base)
set_name = os.path.basename(temp_set)
data_dir = temp_base

# Also create a second directory for list/tuple testing
temp_base2 = tempfile.mkdtemp()
temp_set2 = tempfile.mkdtemp(dir=temp_base2)
set_name2 = os.path.basename(temp_set2)

temp_base3 = tempfile.mkdtemp()
temp_set3 = tempfile.mkdtemp(dir=temp_base3)

data_dir_list = [temp_base2, temp_base3]

ARGS = {
    "data_dir": data_dir,
    "set": set_name,
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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_file Ran
ran on a synthesized input
brummi/derender3d/derender3d/dataloaders.py
code served (permissive licence) · get_code("521cedf170be4833")
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
import torch.nn as nn

# The function is_image_file takes a filename and checks if it ends with
# one of the IMG_EXTENSIONS. It needs a single string parameter.

ARGS = {
    'filename': 'test_image.jpg'
}
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
load_yaml Ran
ran on a synthesized input
brummi/derender3d/derender3d/utils.py
code served (permissive licence) · get_code("c9d96366dfea8bc9")
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 tempfile
import os
import yaml

# Create a temporary YAML file with valid content
temp_dir = tempfile.mkdtemp()
yaml_path = os.path.join(temp_dir, "test_config.yaml")

# Write a simple valid YAML file
config_data = {
    "model": "test_model",
    "batch_size": 32,
    "learning_rate": 0.001,
    "layers": [64, 128, 256]
}

with open(yaml_path, 'w') as f:
    yaml.dump(config_data, f)

ARGS = {
    "path": yaml_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
yaml — 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
mm_normalize Ran
ran on a synthesized input
brummi/derender3d/derender3d/renderer/utils.py
code served (permissive licence) · get_code("0c5ab402075cd7d5")
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 tensor for normalization
x = torch.randn(2, 4)

# Define ARGS dict with all parameters
ARGS = {
    'x': x,
    'min': 0,
    'max': 1
}
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
rand_posneg_range Ran
ran on a synthesized input
brummi/derender3d/derender3d/renderer/utils.py
code served (permissive licence) · get_code("93ba7714c2ce3acc")
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 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 torch

torch.manual_seed(0)

ARGS = {
    "size": 2,
    "min": -5.0,
    "max": 10.0,
}
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 Tensor, 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
rand_range Ran
ran on a synthesized input
brummi/derender3d/derender3d/renderer/utils.py
code served (permissive licence) · get_code("17ad8150640684d6")
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 1, dtype family float, shape (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)

ARGS = {
    "size": 5,
    "min": 0.0,
    "max": 1.0,
}
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 Tensor, ndim 1, dtype family float, shape (5,) — shape (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
to_gamma_space Ran
ran on a synthesized input
brummi/derender3d/derender3d/image_formation_models.py
code served (permissive licence) · get_code("84c2bb6acc6fec73")
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 (2, 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 to_gamma_space takes an image and raises it to the power of GAMMA
# It expects a numeric array-like object (tensor or numpy array)
# We'll create a small tensor to serve as the image

img = torch.tensor([
    [[0.1, 0.2, 0.3, 0.4],
     [0.5, 0.6, 0.7, 0.8]],
    [[0.2, 0.3, 0.4, 0.5],
     [0.6, 0.7, 0.8, 0.9]]
], dtype=torch.float32)

ARGS = {
    'img': img
}
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 3, dtype family float, shape (2, 2, 4) — shape (2, 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
dump_yaml Not yet run
unverified (harvested, no recorded run)
brummi/derender3d/derender3d/utils.py
code served (permissive licence) · get_code("fa8f0dbdb9969655")
How it ran

no invocation recorded.

setup_runtime Not yet run
unverified (harvested, no recorded run)
brummi/derender3d/derender3d/utils.py
code served (permissive licence) · get_code("3083b187271ca1a4")
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, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 0 the same month, 0 later) and 5 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_yaml 4 other papers
4 dated earlier
1911.11130 (2019-11)
Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wild
2011.00844 (2020-11)
Do 2D GANs Know 3D Shape? Unsupervised 3D shape reconstruction from 2D Image GANs
2104.03954 (2021-04)
De-rendering the World's Revolutionary Artefacts
and 1 more not named here
is_image_file 3 other papers
3 dated earlier
1911.11130 (2019-11)
Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wild
2104.03954 (2021-04)
De-rendering the World's Revolutionary Artefacts
2109.02288 (2021-09)
Toward Realistic Single-View 3D Object Reconstruction with Unsupervised Learning from Multiple Images
mm_normalize 3 other papers
3 dated earlier
1911.11130 (2019-11)
Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wild
2011.00844 (2020-11)
Do 2D GANs Know 3D Shape? Unsupervised 3D shape reconstruction from 2D Image GANs
2109.02288 (2021-09)
Toward Realistic Single-View 3D Object Reconstruction with Unsupervised Learning from Multiple Images
rand_posneg_range 3 other papers
3 dated earlier
1911.11130 (2019-11)
Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wild
2011.00844 (2020-11)
Do 2D GANs Know 3D Shape? Unsupervised 3D shape reconstruction from 2D Image GANs
2109.02288 (2021-09)
Toward Realistic Single-View 3D Object Reconstruction with Unsupervised Learning from Multiple Images
rand_range 3 other papers
3 dated earlier
1911.11130 (2019-11)
Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wild
2011.00844 (2020-11)
Do 2D GANs Know 3D Shape? Unsupervised 3D shape reconstruction from 2D Image GANs
2109.02288 (2021-09)
Toward Realistic Single-View 3D Object Reconstruction with Unsupervised Learning from Multiple Images
dump_yaml 2 other papers
2 dated earlier
1911.11130 (2019-11)
Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wild
2109.02288 (2021-09)
Toward Realistic Single-View 3D Object Reconstruction with Unsupervised Learning from Multiple Images

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

Albedo Normals Diffuse Specular Diffuse Specular Rendering Rendering Figure 1. De-rendering 3D objects from in-the-wild images. Left: Our method is trained on unconstrained images with coarse shape estimates which can be obtained using off-the-shelf methods or classical structure from motion. Right: Our method de-renders an image into precise shape, material (diffuse albedo, specularity, specular intensity), and lighting (direction, intensity). The image can then be rerendered and re-lit based on our illumination model. The model generalizes to objects beyond the training categories (e.g. parkingmeter).

For agents

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

get_harvested_code_for_paper("2201.02279")
get_code_for_paper("2201.02279")
have("2201.02279")

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

curl https://syntology.ai/api/ran/2201.02279.json

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

[![Syntology run record](https://syntology.ai/api/ran/2201.02279.svg)](https://syntology.ai/paper/2201.02279)

Connect an agent — have() is free.