Papers › PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows

PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows

28 Jun 2019ICCV 2019 10arXiv:1906.12320archive 2025-07-28

Guandao Yang, Xun Huang, Zekun Hao, Ming-Yu Liu, Serge Belongie, Bharath Hariharan

As 3D point clouds become the representation of choice for multiple vision and graphics applications, the ability to synthesize or reconstruct high-resolution, high-fidelity point clouds becomes crucial. Despite the recent success of deep learning models in discriminative tasks of point clouds, generating point clouds remains challenging. This paper proposes a principled probabilistic framework to generate 3D point clouds by modeling them as a distribution of distributions. Specifically, we learn a two-level hierarchy of distributions where the first level is the distribution of shapes and the second level is the distribution of points given a shape. This formulation allows us to both sample shapes and sample an arbitrary number of points from a shape. Our generative model, named PointFlow, learns each level of the distribution with a continuous normalizing flow. The invertibility of normalizing flows enables the computation of the likelihood during training and allows us to train our model in the variational inference framework. Empirically, we demonstrate that PointFlow achieves state-of-the-art performance in point cloud generation. We additionally show that our model can faithfully reconstruct point clouds and learn useful representations in an unsupervised manner. The code will be available at https://github.com/stevenygd/PointFlow.

PaperPDFConference PDFCodeCode Syntology ran

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 33 code samples harvested from 6 repositories linked to this paper: 18 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 0 violated, 15 with no contract checked; 2 where Syntology's instrument failed) · 15 unverified. Where Syntology's instrument failed: 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 14 samples from 1 repository, 7 ran (7 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 19 samples from 5 repositories, 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.

No sample is linked to this paper from 2 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-24 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 18 samples that ran have no recorded date.

stevenygd/PointFlow officialmentioned in papermentioned on GitHubpytorchMITSyntology: 14 samples, 7 ran (0 instrument-failed) · 7 unverified report
AnTao97/FoldingNet.pytorch mentioned on GitHubpytorchMITSyntology: 9 samples, 8 ran (1 instrument-failed) · 1 unverified report
AnTao97/UnsupervisedPointCloudReconstruction mentioned on GitHubpytorchMITSyntology: not harvested report
gmum/LoCondA mentioned on GitHubpytorchMITSyntology: 3 samples, 1 ran (0 instrument-failed) · 2 unverified report
justinjohn0306/StyleFlow mentioned on GitHubtfSyntology: not harvested report
lmy1001/pointflow_experiment mentioned on GitHubpytorchMITSyntology: 3 samples, 1 ran (1 instrument-failed) · 2 unverified report
maciejzieba/HyperFlow mentioned on GitHubpytorchSyntology: not harvested report
rameenabdal/styleflow mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Controllable and Compositional Generation with Latent-Space Energy-Based Models (arXiv:2110.10873; that paper's own run record: 2 ran (of which 1 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) · 1 unverified); nothing checks that they implement this paper's method. report
rg321/pointFlow_exp mentioned on GitHubpytorchMITSyntology: 3 samples, 0 ran · 3 unverified report
theamaya/3dlatnav mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Diffusion Probabilistic Models for 3D Point Cloud Generation (arXiv:2103.01458; that paper's own run record: 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); nothing checks that they implement this paper's method. report
visinf/s2-flow mentioned on GitHubpytorchApache-2.0Syntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
zekunhao1995/PointFlowRenderer mentioned on GitHubSyntology: not harvested 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

33 samples harvested: 18 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 0 violated, 15 with no contract checked; 2 where Syntology's instrument failed) · 15 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.

1ran · honoured contract
2ran; the contract check could not run
15ran
15unverified

Licence: 5 of the 33 samples are pointer only, meaning Syntology does not serve that copy's text. For 5 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 6 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. “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.

stevenygd/PointFlow official repository 14 samples, 7 ran (0 instrument-failed) · 7 unverified
EMD_CD metrics/evaluation_metrics.py ran MIT (permissive) · c65e6a7584f6c0d1 · report fixture: signature sample_pcs:Tensor/3/float, ref_pcs:Tensor/3/float, batch_size:int/0/int, accelerated_cd:bool/0/bool, reduced:bool/0/bool, accelerated_emd:bool/0/bool · returned dict · level recorded 2026-09-25
bernoulli_log_likelihood utils.py ran MIT (permissive) · 19c5e2db00d325b8 · report fixture: signature x:Tensor/2/float, p:Tensor/2/float, clip:bool/0/bool, eps:float/0/float · returned Tensor · level recorded 2026-09-25
count_parameters in 278 papers models/flow.py ran · honoured contract MIT (permissive) · f6b944f50d3f15ae · report fixture: signature model:callable/0/? · returned int · level recorded, date not recorded
distChamfer in 10 papers metrics/evaluation_metrics.py ran fingerprinted MIT (permissive) here; the stored copy is pointer only · 9a578f2a671a37e4 · report fixture: signature a:Tensor/3/float, b:Tensor/3/float · returned tuple · level recorded 2026-09-26
emd_approx metrics/evaluation_metrics.py ran fingerprinted MIT (permissive) · 16a322ffb874f297 · report fixture: signature x:Tensor/3/float, y:Tensor/3/float · returned Tensor · level recorded 2026-09-25
gaussian_log_likelihood in 9 papers utils.py ran fingerprinted MIT (permissive) · 6306abd15a0062d5 · report fixture: signature x:Tensor/2/float, mean:Tensor/2/float, logvar:Tensor/2/float, clip:bool/0/bool · returned Tensor · level recorded 2026-09-25
kl_diagnormal_stdnormal utils.py ran fingerprinted MIT (permissive) · ad16d0961b8183d2 · report fixture: signature mean:Tensor/2/float, logvar:Tensor/2/float · returned Tensor · level recorded 2026-09-25
add_args in 42 papers args.py unverified MIT (permissive) · 28e9ee719dbcca62 · report
count_nfe models/flow.py unverified MIT (permissive) · 6e88b4b7a2d8cc87 · report
count_total_time models/flow.py unverified MIT (permissive) · ce228183dec2a0fc · report
divergence_approx in 7 papers models/odefunc.py unverified MIT (permissive) here; the stored copy is pointer only · 58625622277c98f5 · report
get_clf_datasets datasets.py unverified MIT (permissive) · ed55e4208dea27ce · report
get_data_loaders in 22 papers datasets.py unverified MIT (permissive) · 92805c7faaa80e02 · report
get_datasets in 49 papers datasets.py unverified MIT (permissive) · 5197b33d0222d257 · report
AnTao97/FoldingNet.pytorch community (archive-listed) 9 samples, 8 ran (1 instrument-failed) · 1 unverified
colormap in 14 papers visualization.py ran MIT (permissive) · 1f2bc333405a5f22 · report fixture: signature x:float/0/float, y:float/0/float, z:float/0/float · returned list · level recorded 2026-09-24
jitter_pointcloud in 7 papers dataset.py ran fingerprinted MIT (permissive) here; the stored copy is pointer only · ca8de2253f873186 · report fixture: signature pointcloud:ndarray/2/float, sigma:float/0/float, clip:float/0/float · returned ndarray · level recorded 2026-09-25
knn in 87 papers
census: 12 implementations from 17 papers, 6 distinct outputs across 4 buckets, one shared input per bucket
model.py ran MIT (permissive) · 7d19991441341d62 · report fixture: signature x:Tensor/3/float, k:int/0/int · returned Tensor · level recorded 2026-09-24
load_pretrain in 11 papers visualization.py ran MIT (permissive) · 4c8ac30cc923c5f2 · report fixture: signature model:callable/0/?, pretrain:str/0/str · returned SimpleModel · level recorded 2026-09-24
local_maxpool model.py ran MIT (permissive) · 8e8beff05c864241 · report fixture: signature x:Tensor/3/float, idx:Tensor/1/int · returned Tensor · level recorded 2026-09-24
rotate_pointcloud dataset.py ran fingerprinted MIT (permissive) · 263eb608d80b44f7 · report fixture: signature pointcloud:ndarray/2/float · returned ndarray · level recorded 2026-09-24
standardize_bbox visualization.py ran fingerprinted MIT (permissive) · b59bf93a1afe4866 · report fixture: signature pcl:ndarray/2/float, points_per_object:int/0/int · returned ndarray · level recorded 2026-09-25
translate_pointcloud in 15 papers dataset.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) here; the stored copy is pointer only · 791051c3e72b67d2 · report fixture: signature pointcloud:ndarray/2/float · returned ndarray · level recorded 2026-09-25
local_cov model.py unverified MIT (permissive) · 38a04fa9c23c641d · report
gmum/LoCondA community (archive-listed) 3 samples, 1 ran (0 instrument-failed) · 2 unverified
get_objects experiments/compute_mesh_metrics.py ran MIT (permissive) · 5bb1776e31d65f3c · report fixture: signature reconstructions_path:PosixPath/0/?, class_name:str/0/str · returned list · level recorded 2026-09-24
get_data_loaders in 22 papers datasets/pointflow.py unverified MIT (permissive) · 423797b5261350e2 · report
get_datasets in 49 papers datasets/pointflow.py unverified MIT (permissive) · bf133ca0a1a7d7e5 · report
lmy1001/pointflow_experiment community (archive-listed) 3 samples, 1 ran (1 instrument-failed) · 2 unverified
stable_var models/normalization.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) here; the stored copy is pointer only · 27ca363b776a43f8 · report fixture: signature x:Tensor/2/float, mean:Tensor/2/float, dim:int/0/int · returned Tensor · level recorded, date not recorded
distChamferCUDA metrics/evaluation_metrics.py unverified MIT (permissive) · 8f015719220a9779 · report
emd_approx metrics/evaluation_metrics.py unverified MIT (permissive) · b3f758ce4a2dc4cd · report
rg321/pointFlow_exp community (archive-listed) 3 samples, 0 ran · 3 unverified
get_clf_datasets datasets.py unverified MIT (permissive) · 24c3329ecdea7b4c · report
get_data_loaders in 22 papers datasets.py unverified MIT (permissive) · 00c2d6048b70226a · report
get_datasets in 49 papers datasets.py unverified MIT (permissive) · 5f63c0ca7dfab72f · report
visinf/s2-flow community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
concat_elu in 8 papers util/array_util.py ran fingerprinted Apache-2.0 (permissive) · d0ea4df0e7ec8ba6 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24

Tasks

Point Cloud GenerationVariational Inference

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Point Cloud Generation ShapeNet Airplane PointFlow 1-NNA-CD 75.68 #5 of 5 Archive leaderboard report
Point Cloud Generation ShapeNet Airplane PointFlow MMD-CD 0.217 #5 of 5 Archive leaderboard report
Point Cloud Generation ShapeNet Car PointFlow 1-NNA-CD 60.65 #4 of 5 Archive leaderboard report
Point Cloud Generation ShapeNet Car PointFlow MMD-CD 0.91 #4 of 5 Archive leaderboard report
Point Cloud Generation ShapeNet Chair PointFlow 1-NNA-CD 60.88 #5 of 5 Archive leaderboard report
Point Cloud Generation ShapeNet Chair PointFlow MMD-CD 2.42 #5 of 5 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Normalizing Flows

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