SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 136830137 · ECCV · 2022

Neural Scene Decoration from a Single Photograph

Duc Nguyen, Yingshu Chen, Sai-Kit Yeung, Binh-Son Hua, Hong-Wing Pang, Phuoc-Hieu Le

Open in the Atlas

Code that ran

9 of 10 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, 2 violated it and 3 have no contract verdict; 4 failures of our instrument; 1 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, measured 2026-11-22; 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/136830137.json · badge: /api/ran/136830137.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
hkust-vgd/neural_scene_decoration canonical (classifier label)
classifier basis: census
9 ran · 1 no recorded run
FunctionStatusWhere it lives
is_power_of_two Ran
ran, violated the contract we drafted
hkust-vgd/neural_scene_decoration/lightweight_gan/lightweight_gan.py
pointer only (licence: MIT); the stored copy get_code serves, from idsia/fpainter, is pointer only (licence: NOASSERTION) · get_code("f8afc5811c6fa56c")
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 idsia/fpainter, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

DiffAugment Ran
ran; our contract draft was wrong, not the code
hkust-vgd/neural_scene_decoration/lightweight_gan/diff_augment.py
code served (permissive licence) · get_code("b3877afdaafbe50f")
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
import random

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

# Create a small batch of images: shape (batch_size, channels, height, width)
# Using distinct sizes: batch=2, channels=3, height=4, width=5
x = torch.randn(2, 3, 4, 5, dtype=torch.float32)

# Test with different augmentation types
types = ['color', 'offset', 'offset_h', 'offset_v', 'translation', 'cutout']

ARGS = {
    'x': x,
    'types': types
}
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
combine_contexts Ran
ran; our contract draft was wrong, not the code
hkust-vgd/neural_scene_decoration/lightweight_gan/lightweight_gan.py
pointer only (licence: MIT); the stored copy get_code serves, from idsia/fpainter, is pointer only (licence: NOASSERTION) · get_code("85f67e8fb251251f")
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 idsia/fpainter, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

convert_rgb Ran
ran on a synthesized input
hkust-vgd/neural_scene_decoration/scenegen/utils.py
code served (permissive licence) · get_code("53ca925cd79d9e3d")
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 Image. 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 PIL import Image

# Create a test image in RGBA mode (not RGB)
test_image = Image.new('RGBA', (4, 3), color=(255, 0, 0, 128))

ARGS = {
    'image': test_image
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int 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
exists Ran
ran, violated the contract we drafted
hkust-vgd/neural_scene_decoration/lightweight_gan/lightweight_gan.py
pointer only (licence: MIT); the stored copy get_code serves, from ThomasMrY/VCT, is pointer only (licence: NONE) · get_code("aa5486a3650902d8")
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 ThomasMrY/VCT, 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.

get_crop_pos Ran
ran on a synthesized input
hkust-vgd/neural_scene_decoration/scenegen/dataset.py
code served (permissive licence) · get_code("77677c68f55d3c9c")
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 1, 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 numpy as np

HEIGHT = 512
SIZE = 512
MARGIN = -1
MAX_X = -1

def get_crop_pos(obj_json, anchor_label, margin=MARGIN):
    if anchor_label is None:
        return (0, MAX_X)
    anchors = [obj for obj in obj_json if obj['class_id'] == anchor_label]
    if len(anchors) > 0:
        anchor = anchors[0]
        anchor_xpos = anchor['centroid'][1] / HEIGHT * SIZE
        right_xpos = max(min(np.floor(anchor_xpos - margin), MAX_X), 0)
        left_xpos = min(max(np.ceil(anchor_xpos + margin - SIZE), 0), MAX_X)
        return (int(left_xpos), int(right_xpos))
    else:
        return (0, MAX_X)

# Construct test arguments
obj_json = [
    {
        'class_id': 1,
        'centroid': [100.0, 256.0]
    },
    {
        'class_id': 2,
        'centroid': [150.0, 384.0]
    }
]

anchor_label = 1

margin = -1

ARGS = {
    'obj_json': obj_json,
    'anchor_label': anchor_label,
    'margin': margin
}
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 1, 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
rand_brightness Ran
ran; our contract draft was wrong, not the code
hkust-vgd/neural_scene_decoration/lightweight_gan/diff_augment.py
pointer only (licence: MIT); the stored copy get_code serves, from postech-cvlab/pytorch-studiogan, is pointer only (licence: NOASSERTION) · get_code("011230b2b9b8fb6f")
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 postech-cvlab/pytorch-studiogan, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

rand_saturation Ran
ran; our contract draft was wrong, not the code
hkust-vgd/neural_scene_decoration/lightweight_gan/diff_augment.py
pointer only (licence: MIT); the stored copy get_code serves, from postech-cvlab/pytorch-studiogan, is pointer only (licence: NOASSERTION) · get_code("5b0d8787e670fc63")
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 postech-cvlab/pytorch-studiogan, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

resize_to_minimum_size Ran
ran on a synthesized input
hkust-vgd/neural_scene_decoration/scenegen/utils.py
code served (permissive licence) · get_code("375ec698ced8f2c5")
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 Image. 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 torchvision
from PIL import Image
import numpy as np

torch.manual_seed(0)

# Create a small PIL Image for testing
# The function expects an image object with a .size attribute
# that returns (width, height)
img_array = np.random.randint(0, 256, (4, 3, 3), dtype=np.uint8)
image = Image.fromarray(img_array.transpose(1, 2, 0))

# min_size parameter - used in comparison with max(*image.size)
min_size = 10

ARGS = {
    "min_size": min_size,
    "image": image
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy, torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int 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
convert_onehot_tensor Not yet run
unverified (harvested, no recorded run)
hkust-vgd/neural_scene_decoration/scenegen/utils.py
code served (permissive licence) · get_code("a1b6b13d08e1b5de")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 6 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 0 the same month, 4 later) and 4 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
exists 486 other papers
75 dated earlier, 347 later, 62 same year, order not determinable, 2 undated · 78 only as an assembly brick
1603.08155 (2016-03)
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
1804.04637 (2018-04)
EMBER: An Open Dataset for Training Static PE Malware Machine Learning Models
and 483 more not named here
rand_brightness 17 other papers
7 dated earlier, 7 later, 3 same year, order not determinable
1912.04958 (2019-12)
Analyzing and Improving the Image Quality of StyleGAN
2006.10738 (2020-06)
Differentiable Augmentation for Data-Efficient GAN Training
2007.15646 (2020-07)
Rewriting a Deep Generative Model
and 14 more not named here
rand_saturation 16 other papers
7 dated earlier, 7 later, 2 same year, order not determinable
1912.04958 (2019-12)
Analyzing and Improving the Image Quality of StyleGAN
2006.10738 (2020-06)
Differentiable Augmentation for Data-Efficient GAN Training
2007.15646 (2020-07)
Rewriting a Deep Generative Model
and 13 more not named here
combine_contexts 5 other papers
2 dated earlier, 1 later, 2 same year, order not determinable
1912.04958 (2019-12)
Analyzing and Improving the Image Quality of StyleGAN
2102.07074 (2021-02)
TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up
2210.06184 (2022-10)
Images as Weight Matrices: Sequential Image Generation Through Synaptic Learning Rules
and 2 more not named here
DiffAugment 2 other papers
2 dated earlier
1912.04958 (2019-12)
Analyzing and Improving the Image Quality of StyleGAN
2006.10738 (2020-06)
Differentiable Augmentation for Data-Efficient GAN Training
is_power_of_two 1 other paper
1 same year, order not determinable
2210.06184 (2022-10)
Images as Weight Matrices: Sequential Image Generation Through Synaptic Learning Rules

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

Furnishing and rendering indoor scenes has been a longstanding task for interior design, where artists create a conceptual design for the space, build a 3D model of the space, decorate, and then perform rendering. Although the task is important, it is tedious and requires tremendous effort. In this paper, we introduce a new problem of domainspecific indoor scene image synthesis, namely neural scene decoration. Given a photograph of an empty indoor space and a list of decorations with layout determined by user, we aim to synthesize a new image of the same space with desired furnishing and decorations. Neural scene decoration can be applied to create conceptual interior designs in a simple yet effective manner. Our attempt to this research problem is a novel scene generation architecture that transforms an empty scene and an object layout into a realistic furnished scene photograph. We demonstrate the performance of our proposed method by comparing it with conditional image synthesis baselines built upon prevailing image translation approaches both qualitatively and quantitatively. We conduct extensive experiments to further validate the plausibility and aesthetics of our generated scenes. Our implementation is available at https:// github.com/hkust-vgd/neural_scene_decoration.

For agents

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

get_harvested_code_for_paper("136830137")
get_code_for_paper("136830137")
have("136830137")

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

curl https://syntology.ai/api/ran/136830137.json

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

[![Syntology run record](https://syntology.ai/api/ran/136830137.svg)](https://syntology.ai/paper/136830137)

Connect an agent — have() is free.