Papers › SemCity: Semantic Scene Generation with Triplane Diffusion

SemCity: Semantic Scene Generation with Triplane Diffusion

12 Mar 2024CVPR 2024 1arXiv:2403.07773archive 2025-07-28

Jumin Lee, Sebin Lee, Changho Jo, Woobin Im, Juhyeong Seon, Sung-Eui Yoon

We present "SemCity," a 3D diffusion model for semantic scene generation in real-world outdoor environments. Most 3D diffusion models focus on generating a single object, synthetic indoor scenes, or synthetic outdoor scenes, while the generation of real-world outdoor scenes is rarely addressed. In this paper, we concentrate on generating a real-outdoor scene through learning a diffusion model on a real-world outdoor dataset. In contrast to synthetic data, real-outdoor datasets often contain more empty spaces due to sensor limitations, causing challenges in learning real-outdoor distributions. To address this issue, we exploit a triplane representation as a proxy form of scene distributions to be learned by our diffusion model. Furthermore, we propose a triplane manipulation that integrates seamlessly with our triplane diffusion model. The manipulation improves our diffusion model's applicability in a variety of downstream tasks related to outdoor scene generation such as scene inpainting, scene outpainting, and semantic scene completion refinements. In experimental results, we demonstrate that our triplane diffusion model shows meaningful generation results compared with existing work in a real-outdoor dataset, SemanticKITTI. We also show our triplane manipulation facilitates seamlessly adding, removing, or modifying objects within a scene. Further, it also enables the expansion of scenes toward a city-level scale. Finally, we evaluate our method on semantic scene completion refinements where our diffusion model enhances predictions of semantic scene completion networks by learning scene distribution. Our code is available at https://github.com/zoomin-lee/SemCity.

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 22 code samples harvested from 1 repository linked to this paper: 18 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 3 honoured, 0 violated, 7 with no contract checked; 8 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 22 samples from 1 repository, 18 ran (10 with no instrument failure; 8 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 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 4 of the 18 samples that ran have no recorded date.

zoomin-lee/semcity officialmentioned in papermentioned on GitHubpytorchMITSyntology: 22 samples, 18 ran (8 instrument-failed) · 4 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

22 samples harvested: 18 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 3 honoured, 0 violated, 7 with no contract checked; 8 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · honoured contract
6ran · our draft was wrong
2ran; the contract check could not run
7ran
4unverified

Licence: 10 of the 22 samples are pointer only, meaning Syntology does not serve that copy's text. For 10 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from zoomin-lee/semcity. “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”. “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.

zoomin-lee/semcity official repository 22 samples, 18 ran (8 instrument-failed) · 4 unverified
TriplaneConv diffusion/unet_triplane.py ran · metamorphic tier: deterministic MIT (permissive) · b3036001ee3ed95e · report fixture: signature featmaps:tuple/1/Tensor · returned tuple · level recorded 2026-09-22
TriplaneDownsample2x diffusion/unet_triplane.py ran · metamorphic tier: deterministic MIT (permissive) · ff17b7bc4046558e · report fixture: signature featmaps:tuple/1/Tensor · returned tuple · level recorded 2026-09-22
TriplaneUpsample2x diffusion/unet_triplane.py ran MIT (permissive) · 98c1fed464e645bb · report fixture: signature featmaps:tuple/1/Tensor · returned tuple · level recorded 2026-09-24
approx_standard_normal_cdf in 150 papers
census: 4 implementations from 14 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
diffusion/losses.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · cfd76fd0d89574a4 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded, date not recorded
betas_for_alpha_bar in 123 papers diffusion/gaussian_diffusion.py ran · honoured contract MIT (permissive) here; the stored copy is pointer only · 2ab2316ac6fdd869 · report fixture: signature num_diffusion_timesteps:int/0/int, alpha_bar:callable/0/?, max_beta:float/0/float · returned ndarray · level recorded, date not recorded
compute_tdf dataset/kitti_dataset.py ran MIT (permissive) · 87ef5d1a6cbdb58b · report fixture: signature voxel_label:ndarray/3/int, trunc_distance:float/0/float, trunc_value:float/0/float · returned ndarray · level recorded 2026-09-24
decompose_featmaps diffusion/unet_triplane.py ran; the contract check could not run (RAISES) MIT (permissive) · 2c048a12482e6f52 · report fixture: signature composed_map:Tensor/4/float, tri_size:tuple/1/int, transpose:bool/0/bool · returned tuple · level recorded 2026-09-22
discretized_gaussian_log_likelihood in 124 papers
census: 6 implementations from 10 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32 · arg 3: rank 2, kind float, dtype float32
diffusion/losses.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · cd33283d615fb3d7 · report fixture: signature x:Tensor/2/float, means:Tensor/2/float, log_scales:Tensor/2/float · returned Tensor · level recorded, date not recorded
flip in 32 papers
census: 3 implementations from 5 papers, 2 distinct outputs on one shared input
dataset/kitti_dataset.py ran MIT (permissive) · dda2d38f31cffc71 · report fixture: signature voxel:ndarray/3/float, invalid:ndarray/3/bool, flip_dim:int/0/int · returned tuple · level recorded 2026-09-24
get_named_beta_schedule in 119 papers diffusion/gaussian_diffusion.py ran · honoured contract MIT (permissive) here; the stored copy is pointer only · a086d6286a40b889 · report fixture: signature schedule_name:str/0/str, num_diffusion_timesteps:int/0/int · returned ndarray · level recorded, date not recorded
get_param_groups_and_shapes in 73 papers diffusion/fp16_util.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · e41367ad14ff58fd · report fixture: signature named_model_params:list/1/tuple · returned list · level recorded 2026-09-24
get_query in 19 papers dataset/kitti_dataset.py ran MIT (permissive) · 9a009f7bfad56ea2 · report fixture: signature voxel_label:ndarray/3/int, num_class:int/0/int, grid_size:tuple/1/int, max_points:int/0/int · returned tuple · level recorded 2026-09-24
make_master_params in 90 papers diffusion/fp16_util.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · e20dd5102da3b050 · report fixture: signature param_groups_and_shapes:list/1/tuple · returned list · level recorded 2026-09-24
make_output_format in 88 papers diffusion/logger.py ran · our draft was wrong MIT (permissive) · bcd8b4acab199405 · report fixture: signature format:str/0/str, ev_dir:str/0/str, log_suffix:str/0/str · returned HumanOutputFormat · level recorded 2026-09-24
mask_img diffusion/nn.py ran MIT (permissive) · 892ae51921341521 · report fixture: signature img:Tensor/4/float, cond:Tensor/4/float, mode:str/0/str, overlap:int/0/int, H:list/1/int · returned Tensor · level recorded 2026-09-24
mpi_weighted_mean in 55 papers diffusion/logger.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · e515a67f7f32e76d · report fixture: signature comm:MockComm/0/?, local_name2valcount:dict/0/? · returned dict · level recorded 2026-09-26
normal_kl in 188 papers
census: 14 implementations from 24 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32 · arg 3: rank 2, kind float, dtype float32 · arg 4: rank 2, kind float, dtype float32
diffusion/losses.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · cf2798b666b231ca · report fixture: signature mean1:Tensor/2/float, logvar1:Tensor/2/float, mean2:Tensor/2/float, logvar2:Tensor/2/float · returned Tensor · level recorded 2026-09-22
unflatten_master_params in 90 papers diffusion/fp16_util.py ran; the contract check could not run (RAISES) MIT (permissive) here; the stored copy is pointer only · 64fff1e30802b815 · report fixture: signature param_group:list/1/tuple, master_param:Tensor/1/float · returned tuple · level recorded 2026-09-24
TriplaneResBlock diffusion/unet_triplane.py unverified MIT (permissive) · fe0e214e83341048 · report
TriplaneUNetModel diffusion/unet_triplane.py unverified MIT (permissive) · 8e7981a79272ed82 · report
compose_featmaps diffusion/unet_triplane.py unverified MIT (permissive) · 58f62059adb7a36e · report
profile in 89 papers diffusion/logger.py unverified MIT (permissive) here; the stored copy is pointer only · 0c6607473a4c4c55 · 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 SemCity (graph method: SemCity). 21 bricks; individually on a fixture: 13 ran (of which 3 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 8 unverified. The assembly has not been run end-to-end.

  1. TriplaneUNetModel entry · level 0 · unverified · 8e7981a79272ed82
  2. SiLU helper · level 1 · ran · 5465fa33e2f8631e
  3. TimestepEmbedSequential model · level 0 · unverified · ed74c5af0b1d1d51
  4. TriplaneConv model · level 1 · ran · b3036001ee3ed95e
  5. TriplaneDownsample2x model · level 1 · ran · ff17b7bc4046558e
  6. TriplaneNorm model · level 1 · ran · af4e0bdd202a4062
  7. TriplaneResBlock model · level 0 · unverified · fe0e214e83341048
  8. TriplaneSiLU model · level 1 · ran · 462d70c6887d1909
  9. TriplaneUpsample2x model · level 1 · ran · 98c1fed464e645bb
  10. compose_featmaps helper · level 0 · unverified · 58f62059adb7a36e
  11. convert_module_to_f16 helper · level 0 · unverified · ac07425399caf784
  12. convert_module_to_f32 helper · level 0 · unverified · b283a8ab305dc007
  13. decompose_featmaps helper · level 1 · ran; the contract check could not run (RAISES) · 2c048a12482e6f52
  14. linear helper · level 1 · ran · our draft was wrong · 0e30585f04efffbe
  15. timestep_embedding helper · level 1 · ran · our draft was wrong · 88867f4df8cef2a9
  16. TimestepBlock helper · level 0 · unverified · 40fb9bc947892adc
  17. normalization helper · level 1 · ran · our draft was wrong · 5b31715a9b105926
  18. checkpoint helper · level 0 · unverified · fb150e1f7e53041e
  19. zero_module helper · level 1 · ran · our draft was wrong · 129b804760b3115f
  20. GroupNorm32 helper · level 1 · ran · 426c2385fa431d9a
  21. CheckpointFunction helper · level 1 · ran · 27faeacc0d8cf344

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="2403.07773") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Scene Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

DiffusionFocus

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