Papers › CommonScenes: Generating Commonsense 3D Indoor Scenes with Scene Graph Diffusion

CommonScenes: Generating Commonsense 3D Indoor Scenes with Scene Graph Diffusion

25 May 2023NeurIPS 2023 11arXiv:2305.16283archive 2025-07-28

Guangyao Zhai, Evin Pınar Örnek, Shun-Cheng Wu, Yan Di, Federico Tombari, Nassir Navab, Benjamin Busam

Controllable scene synthesis aims to create interactive environments for various industrial use cases. Scene graphs provide a highly suitable interface to facilitate these applications by abstracting the scene context in a compact manner. Existing methods, reliant on retrieval from extensive databases or pre-trained shape embeddings, often overlook scene-object and object-object relationships, leading to inconsistent results due to their limited generation capacity. To address this issue, we present CommonScenes, a fully generative model that converts scene graphs into corresponding controllable 3D scenes, which are semantically realistic and conform to commonsense. Our pipeline consists of two branches, one predicting the overall scene layout via a variational auto-encoder and the other generating compatible shapes via latent diffusion, capturing global scene-object and local inter-object relationships in the scene graph while preserving shape diversity. The generated scenes can be manipulated by editing the input scene graph and sampling the noise in the diffusion model. Due to lacking a scene graph dataset offering high-quality object-level meshes with relations, we also construct SG-FRONT, enriching the off-the-shelf indoor dataset 3D-FRONT with additional scene graph labels. Extensive experiments are conducted on SG-FRONT where CommonScenes shows clear advantages over other methods regarding generation consistency, quality, and diversity. Codes and the dataset will be released upon acceptance.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 25 code samples harvested from 1 repository linked to this paper: 11 ran (of which 6 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 14 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 25 samples from 1 repository, 11 ran (9 with no instrument failure; 2 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 11 samples that ran has no recorded date.

ymxlzgy/commonscenes officialmentioned on GitHubpytorchSyntology: 25 samples, 11 ran (2 instrument-failed) · 14 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

25 samples harvested: 11 ran (of which 6 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 14 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
1ran · our draft was wrong
1ran; the contract check could not run
8ran
14unverified

Licence: 25 of the 25 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from ymxlzgy/commonscenes. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 4 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

ymxlzgy/commonscenes official repository 25 samples, 11 ran (2 instrument-failed) · 14 unverified
BasicTransformerBlock in 22 papers model/networks/diffusion_networks/sg_diff.py ran · metamorphic tier: deterministic no licence file found · pointer only · 0d3d0643f8f2a574 · report fixture: returned BasicTransformerBlock · level recorded 2026-09-22
CrossAttention in 85 papers model/networks/diffusion_networks/sg_diff.py ran · metamorphic tier: deterministic no licence file found · pointer only · feb6629ec7db268f · report fixture: returned CrossAttention · level recorded 2026-09-22
Downsample in 58 papers model/networks/diffusion_networks/sg_diff.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · d30cfba3625bdc96 · report fixture: returned Downsample · level recorded 2026-09-22
FeedForward in 198 papers model/networks/diffusion_networks/sg_diff.py ran · metamorphic tier: deterministic no licence file found · pointer only · 3a6e3f85e7f062a1 · report fixture: returned FeedForward · level recorded 2026-09-22
GEGLU in 20 papers
census: 12 implementations from 12 papers, 1 distinct output on one shared input
model/networks/diffusion_networks/sg_diff.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 6ed2a5bef43f4482 · report fixture: returned GEGLU · level recorded 2026-09-22
QKVAttention in 25 papers model/networks/diffusion_networks/sg_diff.py ran no licence file found · pointer only · 064ef8dd5a9701ed · report fixture: signature qkv:Tensor/3/float · returned Tensor · level recorded 2026-09-24
QKVAttentionLegacy in 20 papers model/networks/diffusion_networks/sg_diff.py ran no licence file found · pointer only · d6ede9e76b7e5eef · report fixture: signature qkv:Tensor/3/float · returned Tensor · level recorded 2026-09-24
Upsample in 77 papers model/networks/diffusion_networks/sg_diff.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · d640984e3a59551c · report fixture: returned Upsample · level recorded 2026-09-22
normalization in 70 papers
census: 4 implementations from 6 papers, 4 distinct outputs across 3 buckets, one shared input per bucket
model/networks/diffusion_networks/sg_diff.py ran · our draft was wrong no licence file found · pointer only · c87e65165f123ae3 · report fixture: signature channels:int/0/int · returned GroupNorm32 · level recorded 2026-09-22
normalize in 638 papers
census: 70 implementations from 82 papers, 51 distinct outputs across 11 buckets, one shared input per bucket this sample: bucket 1 of 11, arg 1: rank 2, kind float, dtype float32
scripts/eval_3dfront.py ran · honoured contract fingerprinted no licence file found · pointer only · f89be01bb146a6f6 · report fixture: signature vertices:ndarray/2/float, scale:int/0/int · returned ndarray · level recorded, date not recorded
timestep_embedding in 79 papers
census: 22 implementations from 27 papers, 6 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 1, kind float, dtype float32
model/networks/diffusion_networks/sg_diff.py ran; the contract check could not run (RAISES) no licence file found · pointer only · b4f50214c2d0199b · report fixture: signature timesteps:Tensor/1/float, dim:int/0/int, max_period:int/0/int, repeat_only:bool/0/bool · returned Tensor · level recorded 2026-09-22
AttentionBlock in 69 papers model/networks/diffusion_networks/sg_diff.py unverified no licence file found · pointer only · f056c6622e5fcfdb · report
DiffusionUNet model/networks/diffusion_networks/sg_diff.py unverified no licence file found · pointer only · fa833533f282d17b · report
SpatialTransformer in 23 papers model/networks/diffusion_networks/sg_diff.py unverified no licence file found · pointer only · 3c85d9c6a2542bd3 · report
SpatialTransformer3D model/networks/diffusion_networks/sg_diff.py unverified no licence file found · pointer only · 80fd2577c9d84f27 · report
TimestepBlock in 11 papers model/networks/diffusion_networks/sg_diff.py unverified no licence file found · pointer only · d6657445a1114767 · report
TimestepEmbedSequential in 28 papers model/networks/diffusion_networks/sg_diff.py unverified no licence file found · pointer only · d72478273c76d0a8 · report
UNet3DModel model/networks/diffusion_networks/sg_diff.py unverified no licence file found · pointer only · db84682088e94737 · report
conv_nd in 94 papers model/networks/diffusion_networks/sg_diff.py unverified no licence file found · pointer only · fc3a8da734d7ed8d · report
convert_module_to_f16 model/networks/diffusion_networks/sg_diff.py unverified no licence file found · pointer only · c4acebba15ea2346 · report
convert_module_to_f32 model/networks/diffusion_networks/sg_diff.py unverified no licence file found · pointer only · 0e6d7f37a0b062f2 · report
init_weights in 109 papers model/networks/diffusion_networks/sg_diff.py unverified no licence file found · pointer only · 7a23d0d554f85e3b · report
parse_data in 16 papers scripts/train_3dfront.py unverified no licence file found · pointer only · 97aa4e594bf780bb · report
sg_diff model/networks/diffusion_networks/sg_diff.py unverified no licence file found · pointer only · af0d816a80ef466d · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for CommonScenes (graph method: CommonScenes). 35 bricks; individually on a fixture: 18 ran (of which 8 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 2 violated, 10 with no contract checked; 5 where Syntology's instrument failed) · 17 unverified. The assembly has not been run end-to-end.

  1. sg_diff entry · level 0 · unverified · af0d816a80ef466d
  2. DiffusionUNet helper · level 0 · unverified · fa833533f282d17b
  3. exists helper · level 1 · ran · violated contract · 608e364a9d2376a3
  4. make_beta_schedule helper · level 1 · ran · honoured contract · 3bd7e0cdbd131fdb
  5. UNet3DModel model · level 0 · unverified · db84682088e94737
  6. AttentionBlock helper · level 0 · unverified · f056c6622e5fcfdb
  7. Downsample helper · level 1 · ran · d30cfba3625bdc96
  8. ResBlock helper · level 0 · unverified · 44fbf9fa0b2cf4ac
  9. SpatialTransformer3D helper · level 0 · unverified · 80fd2577c9d84f27
  10. TimestepEmbedSequential helper · level 0 · unverified · d72478273c76d0a8
  11. Upsample helper · level 1 · ran · d640984e3a59551c
  12. conv_nd helper · level 0 · unverified · fc3a8da734d7ed8d
  13. convert_module_to_f16 helper · level 0 · unverified · c4acebba15ea2346
  14. convert_module_to_f32 helper · level 0 · unverified · 0e6d7f37a0b062f2
  15. linear helper · level 0 · unverified · 7705d2253b6cd3eb
  16. normalization helper · level 1 · ran · our draft was wrong · c87e65165f123ae3
  17. timestep_embedding helper · level 1 · ran; the contract check could not run (RAISES) · b4f50214c2d0199b
  18. zero_module helper · level 1 · ran · our draft was wrong · 129b804760b3115f
  19. QKVAttention helper · level 1 · ran · 064ef8dd5a9701ed
  20. QKVAttentionLegacy helper · level 1 · ran · d6ede9e76b7e5eef
  21. checkpoint helper · level 0 · unverified · 6fe195fcfd10e259
  22. avg_pool_nd helper · level 0 · unverified · 51950b12318e7d94
  23. TimestepBlock helper · level 0 · unverified · d6657445a1114767
  24. BasicTransformerBlock helper · level 1 · ran · 0d3d0643f8f2a574
  25. Normalize helper · level 1 · ran · our draft was wrong · c3a6b977022957cb
  26. init_weights helper · level 0 · unverified · 7a23d0d554f85e3b
  27. SpatialTransformer helper · level 0 · unverified · 3c85d9c6a2542bd3
  28. GroupNorm32 helper · level 1 · ran · da485dc2b10fd6d7
  29. count_flops_attn helper · level 0 · unverified · 0c49097ae6ff37ef
  30. CheckpointFunction helper · level 1 · ran · 69360f5b0cc8f069
  31. CrossAttention helper · level 1 · ran · feb6629ec7db268f
  32. FeedForward helper · level 1 · ran · 3a6e3f85e7f062a1
  33. default helper · level 1 · ran · violated contract · fbf9ec7be545688e
  34. max_neg_value helper · level 1 · ran · our draft was wrong · f2fe51a4a5646c6f
  35. GEGLU helper · level 1 · ran · 6ed2a5bef43f4482

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2305.16283") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

DiversityObjectScene Generation

Datasets

Introduced by this paper, per the archive.

SG-FRONT

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

DiffusionGCN

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections