Papers › Point Cloud Oversegmentation with Graph-Structured Deep Metric Learning

Point Cloud Oversegmentation with Graph-Structured Deep Metric Learning

3 Apr 2019CVPR 2019 6arXiv:1904.02113archive 2025-07-28

Loic Landrieu, Mohamed Boussaha

We propose a new supervized learning framework for oversegmenting 3D point clouds into superpoints. We cast this problem as learning deep embeddings of the local geometry and radiometry of 3D points, such that the border of objects presents high contrasts. The embeddings are computed using a lightweight neural network operating on the points' local neighborhood. Finally, we formulate point cloud oversegmentation as a graph partition problem with respect to the learned embeddings. This new approach allows us to set a new state-of-the-art in point cloud oversegmentation by a significant margin, on a dense indoor dataset (S3DIS) and a sparse outdoor one (vKITTI). Our best solution requires over five times fewer superpoints to reach similar performance than previously published methods on S3DIS. Furthermore, we show that our framework can be used to improve superpoint-based semantic segmentation algorithms, setting a new state-of-the-art for this task as well.

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 13 code samples harvested from 2 repositories linked to this paper: 13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 12 samples from 1 repository, 12 ran (12 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 1 sample from 1 repository, 1 ran (0 with no instrument failure; 1 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 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

loicland/superpoint_graph officialmentioned in papermentioned on GitHubpytorchMITSyntology: 12 samples, 12 ran (0 instrument-failed) · 0 unverified report
jsgaobiao/superpoint_graph mentioned on GitHubpytorchMITSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 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

13 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 0 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 · our draft was wrong
12ran

Licence: 1 of the 13 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, 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 2 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.

loicland/superpoint_graph official repository 12 samples, 12 ran (0 instrument-failed) · 0 unverified
compute_boundary_precision learning/metrics.py ran MIT (permissive) · 53525019df188c6b · report fixture: signature is_transition:Tensor/1/bool, pred_transitions:Tensor/1/bool · returned Tensor · level recorded 2026-09-25
compute_boundary_recall learning/metrics.py ran fingerprinted MIT (permissive) · 3cff4b0c303f38be · report fixture: signature is_transition:Tensor/1/float, pred_transitions:Tensor/1/float · returned Tensor · level recorded 2026-09-25
compute_dist in 7 papers supervized_partition/losses.py ran MIT (permissive) · 2782cfa4e987b0a1 · report fixture: signature embeddings:Tensor/2/float, edg_source:Tensor/1/int, edg_target:Tensor/1/int, dist_type:str/0/str · returned Tensor · level recorded 2026-09-25
compute_loss in 97 papers
census: 11 implementations from 11 papers, 9 distinct outputs across 7 buckets, one shared input per bucket
supervized_partition/losses.py ran MIT (permissive) · 851ed5d8a57bf8c7 · report fixture: signature args:Args/0/?, diff:Tensor/1/float, is_transition:Tensor/1/int, weights_loss:Tensor/1/float · returned tuple · level recorded 2026-09-25
compute_predicted_transitions learning/metrics.py ran MIT (permissive) · f6312733479ecec8 · report fixture: signature in_component:Tensor/1/int, edg_source:Tensor/1/int, edg_target:Tensor/1/int · returned Tensor · level recorded 2026-09-25
get_info in 12 papers learning/custom_dataset.py ran MIT (permissive) · 787baadda400bd94 · report fixture: signature args:Args/0/? · returned dict · level recorded 2026-09-25
get_info in 12 papers learning/s3dis_dataset.py ran MIT (permissive) · ba1f19c5139c4825 · report fixture: signature args:Args/0/? · returned dict · level recorded 2026-09-25
get_info in 12 papers learning/sema3d_dataset.py ran MIT (permissive) · b36f9b676c19b53b · report fixture: signature args:Args/0/? · returned dict · level recorded 2026-09-25
get_s3dis_info supervized_partition/graph_processing.py ran MIT (permissive) · 834ef8633c9081cb · report fixture: signature args:SimpleArgs/0/? · returned dict · level recorded 2026-09-25
get_sema3d_info supervized_partition/graph_processing.py ran MIT (permissive) · 60d50c0625cc0aa7 · report fixture: signature args:Args/0/? · returned dict · level recorded 2026-09-25
read_structure supervized_partition/graph_processing.py ran MIT (permissive) · cbecc43af2c952d3 · report fixture: signature file_name:str/0/str, read_geof:bool/0/bool · returned tuple · level recorded 2026-09-25
zhang supervized_partition/losses.py ran MIT (permissive) · b08b6b16d4684b7b · report fixture: signature x:Tensor/2/float, lam:float/0/float, dist_type:str/0/str · returned Tensor · level recorded 2026-09-25
jsgaobiao/superpoint_graph community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
create_fnet learning/graphnet.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · e7175798629e58c2 · report fixture: signature widths:list/1/int, orthoinit:bool/0/bool, llbias:bool/0/bool, bnidx:int/0/int · returned Sequential · level recorded 2026-09-22

Tasks

Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semantic Segmentation S3DIS SSP+SPG Mean IoU 68.4 #28 of 54 Archive leaderboard report
Semantic Segmentation S3DIS SSP+SPG Number of params 0.290M #28 of 54 Archive leaderboard report
Semantic Segmentation S3DIS SSP+SPG Params (M) 0.29 #28 of 54 Archive leaderboard report
Semantic Segmentation S3DIS SSP+SPG mAcc 78.3 #28 of 54 Archive leaderboard report
Semantic Segmentation S3DIS SSP+SPG oAcc 87.9 #28 of 54 Archive leaderboard report
Semantic Segmentation S3DIS Area5 SSP+SPG Number of params 290K #50 of 61 Archive leaderboard report
Semantic Segmentation S3DIS Area5 SSP+SPG mAcc 68.2 #50 of 61 Archive leaderboard report
Semantic Segmentation S3DIS Area5 SSP+SPG mIoU 61.7 #50 of 61 Archive leaderboard report
Semantic Segmentation S3DIS Area5 SSP+SPG oAcc 87.9 #50 of 61 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.

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