SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2108.08841 · ICCV · 2021

Graph-to-3D: End-to-End Generation and Manipulation of 3D Scenes Using Scene Graphs

Federico Tombari, Nassir Navab, Fabian Manhardt, Helisa Dhamo

arXiv · PDF · Open in the Atlas

Code that ran

4 of 7 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 2 failures of our instrument; 3 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/2108.08841.json · badge: /api/ran/2108.08841.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
he-dhamo/graphto3d marked official in Papers with Code
Papers with Code archive
4 ran · 3 no recorded run
FunctionStatusWhere it lives
GraphTripleConv Ran
ran on a synthesized input · constructed an object; no result was computed
he-dhamo/graphto3d/model/VAEGAN_SHARED.py
code served (permissive licence) · get_code("3e7b909bf3705fc1")
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 an instance of its own class, GraphTripleConv: the run constructed the object and did not call it, so no result was computed. 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)

# Define ARGS dict with all parameters for GraphTripleConv
ARGS = {
    'input_dim_obj': 4,
    'input_dim_pred': 3,
    'output_dim': 5,
    'hidden_dim': 8,
    'pooling': 'avg',
    'mlp_normalization': 'none',
    'residual': 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 GraphTripleConv — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a GraphTripleConv 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
WeightNetGCN Ran
ran on a synthesized input · constructed an object; no result was computed
he-dhamo/graphto3d/model/VAEGAN_SHARED.py
code served (permissive licence) · get_code("ef59f52c08d1e995")
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 an instance of its own class, WeightNetGCN: the run constructed the object and did not call it, so no result was computed. 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)

# Create small test tensors for the forward pass
# The forward method expects tensors s, p, o with shape (batch_size, feat_dim_in)
batch_size = 2
feat_dim_in1 = 256
feat_dim_in2 = 256
feat_dim = 128

# Create dummy input tensors
s = torch.randn(batch_size, feat_dim_in1)
p = torch.randn(batch_size, feat_dim_in2)
o = torch.randn(batch_size, feat_dim_in1)

ARGS = {
    'feat_dim_in1': 256,
    'feat_dim_in2': 256,
    'feat_dim': 128,
    'separate_s_o': 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 WeightNetGCN — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a WeightNetGCN 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
build_mlp Ran
ran; our contract draft was wrong, not the code
he-dhamo/graphto3d/model/VAEGAN_SHARED.py
code served (permissive licence) · get_code("d5fa2a668d4411e5")
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 = {
    'dim_list': [8, 16, 32, 4],
    'activation': 'relu',
    'batch_norm': 'batch',
    'dropout': 0.1,
    'final_nonlinearity': 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
make_mlp Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
he-dhamo/graphto3d/model/VAEGAN_SHARED.py
code served (permissive licence) · get_code("0845399702547253")
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 = {
    'dim_list': [4, 8, 6, 2],
    'activation': 'relu',
    'batch_norm': 'none',
    'dropout': 0.1,
    'norelu': False
}
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
GraphTripleConvNet Not yet run
unverified (harvested, no recorded run)
he-dhamo/graphto3d/model/VAEGAN_SHARED.py
code served (permissive licence) · get_code("539eaf068851b210")
How it ran

no invocation recorded.

Sg2ScVAEModel Not yet run
unverified (harvested, no recorded run)
he-dhamo/graphto3d/model/VAEGAN_SHARED.py
code served (permissive licence) · get_code("56636d57978a592d")
How it ran

no invocation recorded.

_init_weights Not yet run
unverified (harvested, no recorded run)
he-dhamo/graphto3d/model/VAEGAN_SHARED.py
code served (permissive licence) · get_code("0bb1f65c11193557")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 2 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 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
build_mlp
brick of this paper's assembly: helper
3 other papers
3 later
2402.12259 (2024-02)
Open3DSG: Open-Vocabulary 3D Scene Graphs from Point Clouds with Queryable Objects and Open-Set Relationships
2412.08580 (2024-12)
LAION-SG: An Enhanced Large-Scale Dataset for Training Complex Image-Text Models with Structural Annotations
2502.05874 (2025-02)
MMGDreamer: Mixed-Modality Graph for Geometry-Controllable 3D Indoor Scene Generation
_init_weights
brick of this paper's assembly: helper
1 other paper
1 dated earlier · 1 only as an assembly brick
2006.15327 (2020-06)
Compositional Video Synthesis with Action Graphs

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

Controllable scene synthesis consists of generating 3D information that satisfy underlying specifications. Thereby, these specifications should be abstract, i.e. allowing easy user interaction, whilst providing enough interface for detailed control. Scene graphs are representations of a scene, composed of objects (nodes) and inter-object relationships (edges), proven to be particularly suited for this task, as they allow for semantic control on the generated content. Previous works tackling this task often rely on synthetic data, and retrieve object meshes, which naturally limits the generation capabilities. To circumvent this issue, we instead propose the first work that directly generates shapes from a scene graph in an end-to-end manner. In addition, we show that the same model supports scene modification, using the respective scene graph as interface. Leveraging Graph Convolutional Networks (GCN) we train a variational Auto-Encoder on top of the object and edge categories, as well as 3D shapes and scene layouts, allowing latter sampling of new scenes and shapes.

For agents

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

get_harvested_code_for_paper("2108.08841")
get_code_for_paper("2108.08841")
have("2108.08841")

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

curl https://syntology.ai/api/ran/2108.08841.json

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

[![Syntology run record](https://syntology.ai/api/ran/2108.08841.svg)](https://syntology.ai/paper/2108.08841)

Connect an agent — have() is free.