Papers › SGAligner : 3D Scene Alignment with Scene Graphs

SGAligner : 3D Scene Alignment with Scene Graphs

28 Apr 2023arXiv:2304.14880archive 2025-07-28

Sayan Deb Sarkar, Ondrej Miksik, Marc Pollefeys, Daniel Barath, Iro Armeni

Building 3D scene graphs has recently emerged as a topic in scene representation for several embodied AI applications to represent the world in a structured and rich manner. With their increased use in solving downstream tasks (eg, navigation and room rearrangement), can we leverage and recycle them for creating 3D maps of environments, a pivotal step in agent operation? We focus on the fundamental problem of aligning pairs of 3D scene graphs whose overlap can range from zero to partial and can contain arbitrary changes. We propose SGAligner, the first method for aligning pairs of 3D scene graphs that is robust to in-the-wild scenarios (ie, unknown overlap -- if any -- and changes in the environment). We get inspired by multi-modality knowledge graphs and use contrastive learning to learn a joint, multi-modal embedding space. We evaluate on the 3RScan dataset and further showcase that our method can be used for estimating the transformation between pairs of 3D scenes. Since benchmarks for these tasks are missing, we create them on this dataset. The code, benchmark, and trained models are available on the project website.

PaperPDFCodeCode 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 10 code samples harvested from 1 repository linked to this paper: 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 10 samples from 1 repository, 7 ran (7 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 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

sayands/sgaligner officialmentioned on GitHubpytorchSyntology: 10 samples, 7 ran (0 instrument-failed) · 3 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

10 samples harvested: 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 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.

7ran
3unverified

Licence: 0 of the 10 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 sayands/sgaligner. “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.

sayands/sgaligner official repository 10 samples, 7 ran (0 instrument-failed) · 3 unverified
Embedding in 90 papers src/aligner/sg_aligner.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · b1dbe3c3e8514beb · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
MultiGAT src/aligner/sg_aligner.py ran · metamorphic tier: invariant MIT (permissive) · a9b3588718c4a5eb · report fixture: signature x:Tensor/2/float, edges:Tensor/2/int · returned Tensor · level recorded 2026-09-22
MultiModalFusion src/aligner/sg_aligner.py ran · metamorphic tier: well formed MIT (permissive) · c1e540367f0b88cd · report fixture: signature embs:list/1/Tensor · returned Tensor · level recorded 2026-09-22
NaivePCT src/aligner/sg_aligner.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · bcf1c7281fec9b0f · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
SA in 11 papers src/aligner/sg_aligner.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 2a7653fcd1586778 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
STN3d src/aligner/sg_aligner.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 8b723461b4045828 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
STNkd src/aligner/sg_aligner.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 7bdfb2479e4f7a3e · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
BaseNetwork in 19 papers src/aligner/sg_aligner.py unverified MIT (permissive) · a7f3284931ce23a3 · report
MultiModalEncoder src/aligner/sg_aligner.py unverified MIT (permissive) · a1845bb6689c837a · report
PointNetfeat src/aligner/sg_aligner.py unverified MIT (permissive) · fdc7a053313b0a64 · report

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.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for SGAligner (graph method: SGAligner). 10 bricks; individually on a fixture: 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

  1. MultiModalEncoder entry · level 0 · unverified · a1845bb6689c837a
  2. MultiGAT helper · level 1 · ran · a9b3588718c4a5eb
  3. MultiModalFusion model · level 1 · ran · c1e540367f0b88cd
  4. NaivePCT helper · level 1 · ran · bcf1c7281fec9b0f
  5. PointNetfeat model · level 0 · unverified · fdc7a053313b0a64
  6. Embedding helper · level 1 · ran · b1dbe3c3e8514beb
  7. SA helper · level 1 · ran · 2a7653fcd1586778
  8. BaseNetwork helper · level 0 · unverified · a7f3284931ce23a3
  9. STN3d helper · level 1 · ran · 8b723461b4045828
  10. STNkd helper · level 1 · ran · 7bdfb2479e4f7a3e

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="2304.14880") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

3D Scene Graph AlignmentContrastive LearningKnowledge GraphsPoint Cloud Registration

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Scene Graph Alignment 3DSSG SGAligner F1 89.3 #2 of 2 Archive leaderboard report
3D Scene Graph Alignment 3DSSG SGAligner Hits@1 94.3 #2 of 2 Archive leaderboard report
3D Scene Graph Alignment 3DSSG SGAligner MRR 96.3 #2 of 2 Archive leaderboard report
Point Cloud Registration 3RScan SGAligner CD 0.0111 #2 of 2 Archive leaderboard report
Point Cloud Registration 3RScan SGAligner RRE 1.012 #2 of 2 Archive leaderboard report
Point Cloud Registration 3RScan SGAligner RTE 1.67 #2 of 2 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

Contrastive LearningGAT

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