Papers › GaPro: Box-Supervised 3D Point Cloud Instance Segmentation Using Gaussian Processes as...

GaPro: Box-Supervised 3D Point Cloud Instance Segmentation Using Gaussian Processes as Pseudo Labelers

25 Jul 2023ICCV 2023 1arXiv:2307.13251archive 2025-07-28

Tuan Duc Ngo, Binh-Son Hua, Khoi Nguyen

Instance segmentation on 3D point clouds (3DIS) is a longstanding challenge in computer vision, where state-of-the-art methods are mainly based on full supervision. As annotating ground truth dense instance masks is tedious and expensive, solving 3DIS with weak supervision has become more practical. In this paper, we propose GaPro, a new instance segmentation for 3D point clouds using axis-aligned 3D bounding box supervision. Our two-step approach involves generating pseudo labels from box annotations and training a 3DIS network with the resulting labels. Additionally, we employ the self-training strategy to improve the performance of our method further. We devise an effective Gaussian Process to generate pseudo instance masks from the bounding boxes and resolve ambiguities when they overlap, resulting in pseudo instance masks with their uncertainty values. Our experiments show that GaPro outperforms previous weakly supervised 3D instance segmentation methods and has competitive performance compared to state-of-the-art fully supervised ones. Furthermore, we demonstrate the robustness of our approach, where we can adapt various state-of-the-art fully supervised methods to the weak supervision task by using our pseudo labels for training. The source code and trained models are available at https://github.com/VinAIResearch/GaPro.

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 14 code samples harvested from 1 repository linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 14 samples from 1 repository, 10 ran (10 with no instrument failure; 0 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 on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

vinairesearch/gapro officialmentioned in papermentioned on GitHubpytorchBSD-3-ClauseSyntology: 14 samples, 10 ran (0 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

14 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 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 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.

10ran
4unverified

Licence: 4 of the 14 samples are pointer only, meaning Syntology does not serve that copy's text. For 4 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 vinairesearch/gapro. “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.

vinairesearch/gapro official repository 14 samples, 10 ran (0 instrument-failed) · 4 unverified
batch_giou_cross gapro/gen_ps_utils.py ran fingerprinted BSD-3-Clause (permissive) · a82dc28b0b035dcf · report fixture: signature boxes1:Tensor/2/float, boxes2:Tensor/2/float · returned tuple · level recorded 2026-09-24
cal_iou in 8 papers gapro/eval_ps_labels.py ran fingerprinted BSD-3-Clause (permissive) · a99c6bd8fd457ccf · report fixture: signature label:Tensor/2/float, ps_label:Tensor/2/float · returned Tensor · level recorded 2026-09-24
farthest_point_sample in 64 papers gapro/gen_ps_utils.py ran fingerprinted BSD-3-Clause (permissive) · 04d97b830ba08cce · report fixture: signature xyz:Tensor/2/float, npoint:int/0/int · returned Tensor · level recorded 2026-09-24
fit_regression_model gapro/gaussian_process_utils.py ran BSD-3-Clause (permissive) · c10a48fe19254b7b · report fixture: signature feats:Tensor/2/float, spp:NoneType/0/?, b1_inds:Tensor/1/int, b2_inds:Tensor/1/int, intersect_inds:Tensor/1/int, training_iter:int/0/int · returned tuple · level recorded 2026-09-24
get_cropped_instance_label gapro/gen_ps_utils.py ran BSD-3-Clause (permissive) · e74d1436766eaa5d · report fixture: signature instance_label:Tensor/1/int, valid_idxs:Tensor/1/int · returned Tensor · level recorded 2026-09-24
get_miou_scene gapro/eval_ps_labels.py ran BSD-3-Clause (permissive) · e113ee75cc13522d · report fixture: signature semantic_label:Tensor/1/int, instance_label:Tensor/1/int, ps_semantic_label:Tensor/1/int, ps_instance_label:Tensor/1/int · returned Tensor · level recorded 2026-09-24
get_normal in 5 papers gapro/scannet_planes.py ran BSD-3-Clause (permissive) · 337cfe91f337fc76 · report fixture: signature quad_vert:list/1/list, center:ndarray/1/float · returned ndarray · level recorded 2026-09-24
isFourPointsInSamePlane gapro/scannet_planes.py ran BSD-3-Clause (permissive) · 5277ce17d186adec · report fixture: signature p0:Tensor/1/float, p1:Tensor/1/float, p2:Tensor/1/float, p3:Tensor/1/float, error:float/0/float · returned bool · level recorded 2026-09-24
read_scene_txt ISBNet/dataset/s3dis/prepare_s3dis.py ran BSD-3-Clause (permissive) here; the stored copy is pointer only · dc19cf51681364ec · report fixture: signature name:str/0/str, data_dir:str/0/str · returned ndarray · level recorded 2026-09-24
rectangle in 7 papers gapro/scannet_planes.py ran fingerprinted BSD-3-Clause (permissive) · 539f79ffe2705afc · report fixture: signature quad_vert:ndarray/2/float, center:ndarray/1/float · returned ndarray · level recorded 2026-09-24
get_labels in 42 papers ISBNet/dataset/s3dis/prepare_s3dis.py unverified BSD-3-Clause (permissive) here; the stored copy is pointer only · 8243d5b09b3ae9c1 · report
get_miou_scene2 gapro/eval_ps_labels.py unverified BSD-3-Clause (permissive) · 7461f69b6ebe6a9d · report
get_pred_color ISBNet/visualization/vis_s3dis.py unverified BSD-3-Clause (permissive) here; the stored copy is pointer only · 206ea004dfc0e7f5 · report
get_pred_color ISBNet/visualization/vis_scannetv2.py unverified BSD-3-Clause (permissive) here; the stored copy is pointer only · 1805fbb9f0a88569 · report

Tasks

3D Instance SegmentationGaussian ProcessesInstance SegmentationSegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Gaussian Process

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