Papers › Diffusion Probabilistic Models for 3D Point Cloud Generation

Diffusion Probabilistic Models for 3D Point Cloud Generation

2 Mar 2021CVPR 2021 1arXiv:2103.01458archive 2025-07-28

Shitong Luo, Wei Hu

We present a probabilistic model for point cloud generation, which is fundamental for various 3D vision tasks such as shape completion, upsampling, synthesis and data augmentation. Inspired by the diffusion process in non-equilibrium thermodynamics, we view points in point clouds as particles in a thermodynamic system in contact with a heat bath, which diffuse from the original distribution to a noise distribution. Point cloud generation thus amounts to learning the reverse diffusion process that transforms the noise distribution to the distribution of a desired shape. Specifically, we propose to model the reverse diffusion process for point clouds as a Markov chain conditioned on certain shape latent. We derive the variational bound in closed form for training and provide implementations of the model. Experimental results demonstrate that our model achieves competitive performance in point cloud generation and auto-encoding. The code is available at https://github.com/luost26/diffusion-point-cloud.

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 29 code samples: 28 from 3 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 29: 22 ran (of which 11 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 10 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 10 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 2 samples from 1 repository, 2 ran (2 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 26 samples from 2 repositories, 19 ran (9 with no instrument failure; 10 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. 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 on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

luost26/diffusion-point-cloud officialmentioned in papermentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
fpthink/PDGN mentioned on GitHubpytorchSyntology: 25 samples, 19 ran (10 instrument-failed) · 6 unverified report
theamaya/3dlatnav mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 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

29 samples harvested: 22 ran (of which 11 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 10 where Syntology's instrument failed) · 7 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
10ran; the contract check could not run
11ran
7unverified

Licence: 2 of the 29 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 3 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. 1 sample is listed last, in a group without a repository. “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 2 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.

luost26/diffusion-point-cloud official repository 2 samples, 2 ran (0 instrument-failed) · 0 unverified
DiffusionPoint models/diffusion.py ran · metamorphic tier: deterministic MIT (permissive) · c89046ee64346e9f · report fixture: returned DiffusionPoint · level recorded 2026-09-22
VarianceSchedule models/diffusion.py ran · metamorphic tier: deterministic MIT (permissive) · 380bb5e9ac8495db · report fixture: returned VarianceSchedule · level recorded 2026-09-22
fpthink/PDGN community (archive-listed) 25 samples, 19 ran (10 instrument-failed) · 6 unverified
PointDiscriminator_1 models/PDGNet.py ran MIT (permissive) · 25204c1fdea83487 · report fixture: returned PointDiscriminator_1 · level recorded 2026-09-22
PointDiscriminator_2 models/PDGNet.py ran MIT (permissive) · f9dca246807b4fad · report fixture: returned PointDiscriminator_2 · level recorded 2026-09-22
PointDiscriminator_3 models/PDGNet.py ran MIT (permissive) · 35cbd79bd975fc0c · report fixture: returned PointDiscriminator_3 · level recorded 2026-09-22
PointDiscriminator_4 models/PDGNet.py ran MIT (permissive) · 88b6db90221f3084 · report fixture: returned PointDiscriminator_4 · level recorded 2026-09-22
ShapeNetCore models/PDGNet.py ran MIT (permissive) · 6e626337710c79fd · report fixture: returned ShapeNetCore · level recorded 2026-09-22
bilateral_block_l1 models/PDGNet.py ran MIT (permissive) · 6c87f76cd845e511 · report fixture: returned bilateral_block_l1 · level recorded 2026-09-22
bilateral_upsample_edgeConv models/PDGNet.py ran MIT (permissive) · cde1974d0e8c3464 · report fixture: returned bilateral_upsample_edgeConv · level recorded 2026-09-22
conv2dbr models/PDGNet.py ran fingerprinted MIT (permissive) · 8617c57ff67112bf · report fixture: returned conv2dbr · level recorded 2026-09-22
get_edge_features in 5 papers models/PDGNet.py ran; the contract check could not run (RAISES) MIT (permissive) · 1e042976d61e8c8a · report fixture: signature x:Tensor/3/float, k:int/0/int, num:int/0/int · returned Tensor · level recorded 2026-09-22
get_edge_features_xyz models/PDGNet.py ran; the contract check could not run (RAISES) MIT (permissive) · 096e5ea95c5f7eb6 · report fixture: signature x:Tensor/3/float, pc:Tensor/3/float, k:int/0/int, num:int/0/int · returned tuple · level recorded 2026-09-22
jitter_point_cloud models/PDGNet.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · bdd7784c7336e843 · report fixture: signature batch_data:ndarray/3/float, sigma:float/0/float, clip:float/0/float · returned ndarray · level recorded 2026-09-22
random_scale_point_cloud models/PDGNet.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · c4bfd74b0f6a7d8d · report fixture: signature batch_data:ndarray/3/float, scale_low:float/0/float, scale_high:float/0/float · returned ndarray · level recorded 2026-09-22
rotate_perturbation_point_cloud models/PDGNet.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 79446b78c27526f0 · report fixture: signature batch_data:ndarray/3/float, angle_sigma:float/0/float, angle_clip:float/0/float · returned ndarray · level recorded 2026-09-22
rotate_perturbation_point_cloud_with_normal models/PDGNet.py ran; the contract check could not run (RAISES) MIT (permissive) · 3db497496c6e4cc0 · report fixture: signature batch_data:ndarray/3/float, angle_sigma:float/0/float, angle_clip:float/0/float · returned ndarray · level recorded 2026-09-22
rotate_point_cloud in 17 papers models/PDGNet.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · adb85367d5bf360a · report fixture: signature batch_data:ndarray/3/float · returned ndarray · level recorded 2026-09-22
rotate_point_cloud_with_normal models/PDGNet.py ran; the contract check could not run (RAISES) MIT (permissive) · 9b39b2ae031d10f6 · report fixture: signature batch_xyz_normal:ndarray/3/float · returned ndarray · level recorded 2026-09-22
shift_point_cloud models/PDGNet.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 265977b03f1bbb45 · report fixture: signature batch_data:ndarray/3/float, shift_range:float/0/float · returned ndarray · level recorded 2026-09-22
shuffle_points in 13 papers models/PDGNet.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · a97f76b9c0811c93 · report fixture: signature batch_data:ndarray/3/float · returned ndarray · level recorded 2026-09-22
upsample_edgeConv models/PDGNet.py ran MIT (permissive) · 7f1525d96299a288 · report fixture: returned upsample_edgeConv · level recorded 2026-09-22
ModelNetDataset models/PDGNet.py unverified MIT (permissive) · 96a47b47754cc0a4 · report
PDGNet models/PDGNet.py unverified MIT (permissive) · 0c0259c3ed40c727 · report
PointGenerator models/PDGNet.py unverified MIT (permissive) · 4e304106a8e2b1df · report
bilateral_block_l2 models/PDGNet.py unverified MIT (permissive) · f29c498243b560a7 · report
bilateral_block_l3 models/PDGNet.py unverified MIT (permissive) · f5e60736bb09fc86 · report
bilateral_block_l4 models/PDGNet.py unverified MIT (permissive) · 1bfe4165bf8b09b1 · report
theamaya/3dlatnav community (archive-listed) 1 sample, 0 ran · 1 unverified
DiffusionPoint models/Diffusion/models/diffusion.py unverified no licence file found · pointer only · 1e48b52609d7ac4f · report
Repository not located 1 sample, 1 ran (0 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
pc_normalize in 81 papers
census: 2 implementations from 6 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
repository not located ran · honoured contract fingerprinted licence of this copy not recorded · ec413739d406e611 · report fixture: signature pc:ndarray/2/float · returned ndarray · level recorded 2026-09-22

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. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

3 assemblies on this paper: 3 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

3 sibling assemblies for Diffusion Probabilistic Models (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Diffusion Probabilistic Models (graph method: Diffusion Probabilistic Models). 2 bricks; individually on a fixture: 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 3 siblings

  1. DiffusionPoint entry · level 1 · ran · c89046ee64346e9f
  2. VarianceSchedule scheduler · level 1 · ran · 380bb5e9ac8495db

harvested Assembly for Diffusion Probabilistic Models (graph method: Diffusion Probabilistic Models). 26 bricks; individually on a fixture: 20 ran (of which 9 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 10 where Syntology's instrument failed) · 6 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. PDGNet entry · level 0 · unverified · 0c0259c3ed40c727
  2. ModelNetDataset helper · level 0 · unverified · 96a47b47754cc0a4
  3. PointDiscriminator_1 model · level 1 · ran · 25204c1fdea83487
  4. PointDiscriminator_2 model · level 1 · ran · f9dca246807b4fad
  5. PointDiscriminator_3 model · level 1 · ran · 35cbd79bd975fc0c
  6. PointDiscriminator_4 model · level 1 · ran · 88b6db90221f3084
  7. PointGenerator model · level 0 · unverified · 4e304106a8e2b1df
  8. ShapeNetCore helper · level 1 · ran · 6e626337710c79fd
  9. jitter_point_cloud helper · level 1 · ran; the contract check could not run (RAISES) · bdd7784c7336e843
  10. pc_normalize helper · level 1 · ran · honoured contract · ec413739d406e611
  11. random_scale_point_cloud helper · level 1 · ran; the contract check could not run (RAISES) · c4bfd74b0f6a7d8d
  12. rotate_perturbation_point_cloud helper · level 1 · ran; the contract check could not run (RAISES) · 79446b78c27526f0
  13. rotate_perturbation_point_cloud_with_normal helper · level 1 · ran; the contract check could not run (RAISES) · 3db497496c6e4cc0
  14. rotate_point_cloud helper · level 1 · ran; the contract check could not run (RAISES) · adb85367d5bf360a
  15. rotate_point_cloud_with_normal helper · level 1 · ran; the contract check could not run (RAISES) · 9b39b2ae031d10f6
  16. shift_point_cloud helper · level 1 · ran; the contract check could not run (RAISES) · 265977b03f1bbb45
  17. shuffle_points helper · level 1 · ran; the contract check could not run (RAISES) · a97f76b9c0811c93
  18. bilateral_block_l1 model · level 1 · ran · 6c87f76cd845e511
  19. bilateral_block_l2 model · level 0 · unverified · f29c498243b560a7
  20. bilateral_block_l3 model · level 0 · unverified · f5e60736bb09fc86
  21. bilateral_block_l4 model · level 0 · unverified · 1bfe4165bf8b09b1
  22. upsample_edgeConv helper · level 1 · ran · 7f1525d96299a288
  23. bilateral_upsample_edgeConv helper · level 1 · ran · cde1974d0e8c3464
  24. conv2dbr helper · level 1 · ran · 8617c57ff67112bf
  25. get_edge_features helper · level 1 · ran; the contract check could not run (RAISES) · 1e042976d61e8c8a
  26. get_edge_features_xyz helper · level 1 · ran; the contract check could not run (RAISES) · 096e5ea95c5f7eb6

harvested Assembly for Diffusion Probabilistic Models (graph method: Diffusion Probabilistic Models). 2 bricks; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 3 siblings

  1. DiffusionPoint entry · level 0 · unverified · 1e48b52609d7ac4f
  2. VarianceSchedule scheduler · level 1 · ran · 380bb5e9ac8495db

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="2103.01458") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Data AugmentationPoint Cloud Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Diffusion

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