Papers › 3D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutions

3D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutions

15 May 2019ICCV 2019 10arXiv:1905.06292archive 2025-07-28

Dong Wook Shu, Sung Woo Park, Junseok Kwon

In this paper, we propose a novel generative adversarial network (GAN) for 3D point clouds generation, which is called tree-GAN. To achieve state-of-the-art performance for multi-class 3D point cloud generation, a tree-structured graph convolution network (TreeGCN) is introduced as a generator for tree-GAN. Because TreeGCN performs graph convolutions within a tree, it can use ancestor information to boost the representation power for features. To evaluate GANs for 3D point clouds accurately, we develop a novel evaluation metric called Frechet point cloud distance (FPD). Experimental results demonstrate that the proposed tree-GAN outperforms state-of-the-art GANs in terms of both conventional metrics and FPD, and can generate point clouds for different semantic parts without prior knowledge.

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 25 code samples harvested from 3 repositories linked to this paper: 18 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 1 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: community (archive-listed): 25 samples from 3 repositories, 18 ran (15 with no instrument failure; 3 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.

EricDai0/AdvGCGAN mentioned on GitHubpytorchMITSyntology: 12 samples, 9 ran (3 instrument-failed) · 3 unverified report
jtpils/treegan mentioned on GitHubpytorchnot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-readySyntology: not harvested report
prajwalsingh/TreeGCN-ED mentioned on GitHubtfMITSyntology: 9 samples, 7 ran (0 instrument-failed) · 2 unverified report
prajwalsingh/TreeGCN-GAN mentioned on GitHubtfMITSyntology: 4 samples, 2 ran (0 instrument-failed) · 2 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: 18 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 3 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 last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · our draft was wrong
2ran; the contract check could not run
15ran
7unverified

Licence: 2 of the 25 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 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 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. “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.

EricDai0/AdvGCGAN community (archive-listed) 12 samples, 9 ran (3 instrument-failed) · 3 unverified
SOR defense.py ran MIT (permissive) · 41e39b6bcd645cfb · report fixture: signature points:ndarray/3/float, alpha:float/0/float, k:int/0/int · returned ndarray · level recorded 2026-09-24
SRS defense.py ran fingerprinted MIT (permissive) · 5cfb3f364d06cb8b · report fixture: signature points:ndarray/3/float, percentage:float/0/float · returned ndarray · level recorded 2026-09-24
distChamfer in 10 papers 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
euler2quat in 9 papers eulerangles.py ran fingerprinted MIT (permissive) · 2d9e8ce18f344f58 · report fixture: signature z:float/0/float, y:float/0/float, x:float/0/float · returned ndarray · level recorded 2026-09-24
feature_transform_regularizer in 9 papers models/pointnet.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · e996c64ee89d2b50 · report fixture: signature trans:Tensor/3/float · returned Tensor · level recorded 2026-09-24
get_average_dis evaluate.py ran MIT (permissive) · 2a8d832a5a30956c · report fixture: signature x:Tensor/3/float, k:int/0/int, num:int/0/int · returned Tensor · level recorded 2026-09-24
get_graph_feature in 51 papers
census: 6 implementations from 5 papers, 4 distinct outputs across 2 buckets, one shared input per bucket
models/dgcnn.py ran MIT (permissive) · d4e1cb56cdef48af · report fixture: signature x:Tensor/3/float, k:int/0/int, idx:NoneType/0/? · returned Tensor · level recorded 2026-09-24
knn in 87 papers
census: 12 implementations from 17 papers, 6 distinct outputs across 4 buckets, one shared input per bucket this sample: bucket 1 of 4, arg 1: rank 3, kind float, dtype float32
models/dgcnn.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · cdd0141594039dcb · report fixture: signature x:Tensor/3/float, k:int/0/int · returned Tensor · level recorded 2026-09-22
mat2euler in 10 papers eulerangles.py ran; the contract check could not run (RAISES) MIT (permissive) · dd1f3e0945b180f2 · report fixture: signature M:ndarray/2/float, cy_thresh:NoneType/0/? · returned tuple · level recorded 2026-09-24
distChamferCUDA evaluation_metrics.py unverified MIT (permissive) · 8f015719220a9779 · report
emd_approx evaluation_metrics.py unverified MIT (permissive) · b3f758ce4a2dc4cd · report
euler2mat in 21 papers eulerangles.py unverified MIT (permissive) · c895ee22fc847eed · report
prajwalsingh/TreeGCN-ED community (archive-listed) 9 samples, 7 ran (0 instrument-failed) · 2 unverified
aug_pc utils.py ran fingerprinted MIT (permissive) · bf160a07c8a8b8bd · report fixture: signature pointcloud:ndarray/2/float · returned ndarray · level recorded 2026-09-24
fetch_data in 6 papers utils.py ran MIT (permissive) · fa73af0144d9c1c5 · report fixture: signature path:MockTensorPath/0/? · returned tuple · level recorded 2026-09-24
find_triangle_area Preprocessing_Data/meshtopc.py ran MIT (permissive) · b037cba8391e5a6d · report fixture: signature v1:ndarray/2/float, v2:ndarray/2/float, v3:ndarray/2/float · returned ndarray · level recorded 2026-09-24
load_batch in 18 papers utils.py ran MIT (permissive) · 7d586ed5128718bb · report fixture: signature path:ndarray/2/float, batch_size:int/0/int · returned _BatchDataset · level recorded 2026-09-24
mesh_to_pc Preprocessing_Data/meshtopc.py ran MIT (permissive) · 2331393383bc00db · report fixture: signature vertices:ndarray/2/float, faces:ndarray/2/int, N:int/0/int · returned ndarray · level recorded 2026-09-24
parse_data in 16 papers infer_testresult.py ran MIT (permissive) · fc9e78141623c787 · report fixture: signature data:list/1/str · returned float · level recorded 2026-09-24
pc_normalize in 81 papers
census: 2 implementations from 6 papers, 1 distinct output on one shared input
Preprocessing_Data/mesh_to_pointcloud.py ran fingerprinted MIT (permissive) · 870dbef57748b010 · report fixture: signature pc:ndarray/2/float · returned ndarray · level recorded 2026-09-24
chamfer_distance in 17 papers losses.py unverified MIT (permissive) · d55242abeb8deaae · report
chamfer_loss in 6 papers losses.py unverified MIT (permissive) · 0a1ea77d65404236 · report
prajwalsingh/TreeGCN-GAN community (archive-listed) 4 samples, 2 ran (0 instrument-failed) · 2 unverified
critic_loss_gp losses.py ran MIT (permissive) · 3c2006a89e44a5f3 · report fixture: signature D_real:EagerTensor/1/float, D_fake:EagerTensor/1/float, Y:EagerTensor/3/float, Y_cap:EagerTensor/3/float, model:CriticModel/0/?, batch_size:int/0/int · returned EagerTensor · level recorded 2026-09-24
gen_loss losses.py ran MIT (permissive) · 5452ec5020495768 · report fixture: signature D_fake:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-24
fetch_data in 6 papers utils.py unverified MIT (permissive) · 03ad94b765c74aa7 · report
load_data in 700 papers utils.py unverified MIT (permissive) · 7cd79aa08d856d8c · report

Tasks

Point Cloud Generation

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Convolution

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