Papers › Robust Point Cloud Registration Framework Based on Deep Graph Matching

Robust Point Cloud Registration Framework Based on Deep Graph Matching

7 Mar 2021CVPR 2021 1arXiv:2103.04256archive 2025-07-28

Kexue Fu, Shaolei Liu, Xiaoyuan Luo, Manning Wang

3D point cloud registration is a fundamental problem in computer vision and robotics. There has been extensive research in this area, but existing methods meet great challenges in situations with a large proportion of outliers and time constraints, but without good transformation initialization. Recently, a series of learning-based algorithms have been introduced and show advantages in speed. Many of them are based on correspondences between the two point clouds, so they do not rely on transformation initialization. However, these learning-based methods are sensitive to outliers, which lead to more incorrect correspondences. In this paper, we propose a novel deep graph matchingbased framework for point cloud registration. Specifically, we first transform point clouds into graphs and extract deep features for each point. Then, we develop a module based on deep graph matching to calculate a soft correspondence matrix. By using graph matching, not only the local geometry of each point but also its structure and topology in a larger range are considered in establishing correspondences, so that more correct correspondences are found. We train the network with a loss directly defined on the correspondences, and in the test stage the soft correspondences are transformed into hard one-to-one correspondences so that registration can be performed by singular value decomposition. Furthermore, we introduce a transformer-based method to generate edges for graph construction, which further improves the quality of the correspondences. Extensive experiments on registering clean, noisy, partial-to-partial and unseen category point clouds show that the proposed method achieves state-of-the-art performance. The code will be made publicly available at https://github.com/fukexue/RGM.

PaperPDFConference PDFCodeCode 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 38 code samples harvested from 2 repositories linked to this paper: 26 ran (of which 6 constructed an object rather than computing a result; 20 with no instrument failure: 1 honoured, 0 violated, 19 with no contract checked; 6 where Syntology's instrument failed) · 12 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 3 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 23 samples from 1 repository, 15 ran (11 with no instrument failure; 4 where Syntology's instrument failed); community (archive-listed): 15 samples from 1 repository, 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.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

fukexue/RGM officialmentioned in papermentioned on GitHubpytorchSyntology: 23 samples, 15 ran (4 instrument-failed) · 8 unverified report
zhileichen99/utopic mentioned on GitHubpytorchSyntology: 15 samples, 11 ran (2 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

38 samples harvested: 26 ran (of which 6 constructed an object rather than computing a result; 20 with no instrument failure: 1 honoured, 0 violated, 19 with no contract checked; 6 where Syntology's instrument failed) · 12 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 · honoured contract
3ran · our draft was wrong
3ran; the contract check could not run
19ran
12unverified

Licence: 38 of the 38 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 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”. For 2 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

fukexue/RGM official repository 23 samples, 15 ran (4 instrument-failed) · 8 unverified
Affinity models/Net_noais.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 8ed631cec5e262f2 · report fixture: signature X:Tensor/3/float, Y:Tensor/3/float · returned Tensor · level recorded 2026-09-22
DGCNN in 6 papers models/Net_noais.py ran no licence file found · pointer only · d161b77a736a9841 · report fixture: signature xyz:Tensor/3/float · returned tuple · level recorded 2026-09-24
GMAttendSigmod models/Net_noais.py ran no licence file found · pointer only · dfea0dffb97e8286 · report fixture: signature x:Tensor/3/float, y:Tensor/3/float · returned Tensor · level recorded 2026-09-24
GMAttendSigmod2 models/Net_noais.py ran no licence file found · pointer only · 5665659fd7bb2d36 · report fixture: signature x:Tensor/3/float, y:Tensor/3/float · returned Tensor · level recorded 2026-09-24
GMAttendSoftmax1 models/Net_noais.py ran no licence file found · pointer only · d70f04e35abd05fb · report fixture: signature x:Tensor/3/float, y:Tensor/3/float · returned Tensor · level recorded 2026-09-24
GMAttendSoftmax2 models/Net_noais.py ran no licence file found · pointer only · 9ac916d6842c5bf2 · report fixture: signature x:Tensor/3/float, y:Tensor/3/float · returned Tensor · level recorded 2026-09-24
GMAttendSoftmax3 models/Net_noais.py ran no licence file found · pointer only · 7df8dd52089d875f · report fixture: signature x:Tensor/3/float, y:Tensor/3/float · returned Tensor · level recorded 2026-09-24
Gconv models/Net_noais.py ran · metamorphic tier: invariant no licence file found · pointer only · 344c6a7217686660 · report fixture: signature A:Tensor/3/float, x:Tensor/3/float, norm:bool/0/bool · returned Tensor · level recorded 2026-09-22
MultiHeadedAttention in 38 papers models/Net_noais.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 16726110f1aa6e89 · report fixture: signature query:Tensor/3/float, key:Tensor/3/float, value:Tensor/3/float, mask:NoneType/0/? · returned Tensor · level recorded 2026-09-22
Siamese_Gconv models/Net_noais.py ran · metamorphic tier: deterministic no licence file found · pointer only · 8fd60000985e01f0 · report fixture: signature g1:tuple/1/Tensor, g2:tuple/1/Tensor · returned tuple · level recorded 2026-09-22
angle models/Net_noais.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 4cc43825a7e3f5bc · report fixture: signature v1:Tensor/2/float, v2:Tensor/2/float · returned Tensor · level recorded 2026-09-22
attention in 144 papers
census: 11 implementations from 10 papers, 7 distinct outputs across 5 buckets, one shared input per bucket
models/Net_noais.py ran · our draft was wrong no licence file found · pointer only · c032b5c8af4d2299 · report fixture: signature query:Tensor/3/float, key:Tensor/3/float, value:Tensor/3/float, mask:NoneType/0/?, dropout:NoneType/0/? · returned tuple · level recorded 2026-09-22
compute_affinity models/Net_noais.py ran · honoured contract fingerprinted no licence file found · pointer only · 1fc666385793ccd3 · report fixture: signature feat_distance:Tensor/2/float, alpha:float/0/float · returned Tensor · level recorded 2026-09-22
match_features models/Net_noais.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 1ba154bfd017409c · report fixture: signature feat_src:Tensor/3/float, feat_ref:Tensor/3/float, metric:str/0/str · returned Tensor · level recorded 2026-09-22
square_distance in 89 papers
census: 11 implementations from 18 papers, 4 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 3, kind float, dtype float32 · arg 2: rank 3, kind float, dtype float32
models/Net_noais.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 4db73dd57b5d6162 · report fixture: signature src:Tensor/3/float, dst:Tensor/3/float · returned Tensor · level recorded 2026-09-22
GMAttend models/Net_noais.py unverified no licence file found · pointer only · e13ff06f2f218d2a · report
GMAttendNother models/Net_noais.py unverified no licence file found · pointer only · b9bef27b0e2a1d93 · report
GMAttendSigmod1 models/Net_noais.py unverified no licence file found · pointer only · ff29112fce9e003b · report
GMAttendSoftmax4 models/Net_noais.py unverified no licence file found · pointer only · 98e1d6884d26a55d · report
GMAttendattention models/Net_noais.py unverified no licence file found · pointer only · 0bb01b1fc35ef34d · report
Net in 54 papers models/Net_noais.py unverified no licence file found · pointer only · fcbfadd404cae2d3 · report
Transformer in 173 papers models/Net_noais.py unverified no licence file found · pointer only · 7d02fa050dbc4674 · report
zhileichen99/utopic community (archive-listed) 15 samples, 11 ran (2 instrument-failed) · 4 unverified
AdaptiveConv models/architecture.py ran no licence file found · pointer only · a212bb5f0b2b3059 · report fixture: returned AdaptiveConv · level recorded 2026-09-22
AdaptiveFCN models/architecture.py ran no licence file found · pointer only · 169d4911fd92b68f · report fixture: returned AdaptiveFCN · level recorded 2026-09-22
Affinity models/architecture.py ran no licence file found · pointer only · 1144c464e45696c1 · report fixture: returned Affinity · level recorded 2026-09-22
AttentionLayer in 30 papers models/architecture.py ran no licence file found · pointer only · f8e8754f133cc766 · report fixture: returned AttentionLayer · level recorded 2026-09-22
GeoAttentionLayer models/architecture.py ran no licence file found · pointer only · 4b54ff9833463256 · report fixture: signature input_states:Tensor/3/float, memory_states:Tensor/3/float, position_states:Tensor/4/float, memory_masks:Tensor/2/bool · returned tuple · level recorded 2026-09-24
GeoMultiHeadAttention models/architecture.py ran no licence file found · pointer only · 94d7f5c36cccecf4 · report fixture: returned GeoMultiHeadAttention · level recorded 2026-09-22
MultiHeadAttention in 124 papers
census: 9 implementations from 7 papers, 9 distinct outputs across 3 buckets, one shared input per bucket
models/architecture.py ran no licence file found · pointer only · 11617e778bcd8123 · report fixture: returned MultiHeadAttention · level recorded 2026-09-22
PCN models/architecture.py ran fingerprinted no licence file found · pointer only · e95c69692461a21c · report fixture: signature xyz:Tensor/3/float · returned tuple · level recorded 2026-09-24
TransformerLayer in 34 papers models/architecture.py ran no licence file found · pointer only · 7c8bbdde4d49d75f · report fixture: signature input_states:Tensor/3/float, memory_states:Tensor/3/float, memory_masks:NoneType/0/?, attention_factors:NoneType/0/? · returned tuple · 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/architecture.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 194ab488bb382dbb · report fixture: signature x:Tensor/3/float, k:int/0/int, idx:NoneType/0/?, dim6:bool/0/bool · returned tuple · level recorded 2026-09-22
sinkhorn_rpm models/architecture.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 64cfcde03f2766ff · report fixture: signature log_alpha:Tensor/3/float, n_iters:int/0/int, slack:bool/0/bool, eps:int/0/int · returned Tensor · level recorded 2026-09-22
GeoTransformerLayer models/architecture.py unverified no licence file found · pointer only · 13d948605b2e3e44 · report
GeometryTransformer models/architecture.py unverified no licence file found · pointer only · 9baf6e056ec88f3b · report
PipeLine models/architecture.py unverified no licence file found · pointer only · 98b43be39938d145 · report
TransformerModule in 5 papers models/architecture.py unverified no licence file found · pointer only · d76b3d0a288b4194 · 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. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

2 assemblies on this paper: 2 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

2 sibling assemblies for Robust Point Cloud Registration Framework Based on Deep Graph Matching (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Robust Point Cloud Registration Framework Based on Deep Graph Matching (graph method: Robust Point Cloud Registration Framework Based on Deep Graph Matching). 20 bricks; individually on a fixture: 16 ran (of which 8 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. PipeLine entry · level 0 · unverified · 98b43be39938d145
  2. AdaptiveFCN model · level 1 · ran · 169d4911fd92b68f
  3. Affinity helper · level 1 · ran · 1144c464e45696c1
  4. PCN helper · level 1 · ran · e95c69692461a21c
  5. TransformerModule model · level 0 · unverified · d76b3d0a288b4194
  6. sinkhorn_rpm helper · level 1 · ran; the contract check could not run (RAISES) · 64cfcde03f2766ff
  7. AdaptiveConv helper · level 1 · ran · a212bb5f0b2b3059
  8. get_graph_feature helper · level 1 · ran · our draft was wrong · 194ab488bb382dbb
  9. GeometryTransformer helper · level 0 · unverified · 9baf6e056ec88f3b
  10. knn helper · level 1 · ran; the contract check could not run · cdd0141594039dcb
  11. GeoTransformerLayer helper · level 0 · unverified · 13d948605b2e3e44
  12. TransformerLayer helper · level 1 · ran · 7c8bbdde4d49d75f
  13. AttentionOutput helper · level 1 · ran · 6677d98e9f15a143
  14. GeoAttentionLayer helper · level 1 · ran · 4b54ff9833463256
  15. AttentionLayer helper · level 1 · ran · f8e8754f133cc766
  16. get_activation helper · level 1 · ran · our draft was wrong · e8d13647b3b416c0
  17. get_dropout helper · level 1 · ran · our draft was wrong · 8629de50bd3cc48f
  18. GeoMultiHeadAttention helper · level 1 · ran · 94d7f5c36cccecf4
  19. MultiHeadAttention helper · level 1 · ran · 11617e778bcd8123
  20. MonteCarloDropout helper · level 1 · ran · cedfc23285e99bea

harvested Assembly for Robust Point Cloud Registration Framework Based on Deep Graph Matching (graph method: Robust Point Cloud Registration Framework Based on Deep Graph Matching). 34 bricks; individually on a fixture: 26 ran (of which 1 constructed an object rather than computing a result; 19 with no instrument failure: 1 honoured, 0 violated, 18 with no contract checked; 7 where Syntology's instrument failed) · 8 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. Net entry · level 0 · unverified · fcbfadd404cae2d3
  2. Affinity helper · level 1 · ran · 8ed631cec5e262f2
  3. DGCNN model · level 1 · ran · d161b77a736a9841
  4. GMAttend helper · level 0 · unverified · e13ff06f2f218d2a
  5. GMAttendNother helper · level 0 · unverified · b9bef27b0e2a1d93
  6. GMAttendSigmod helper · level 1 · ran · dfea0dffb97e8286
  7. GMAttendSigmod1 helper · level 0 · unverified · ff29112fce9e003b
  8. GMAttendSigmod2 helper · level 1 · ran · 5665659fd7bb2d36
  9. GMAttendSoftmax1 helper · level 1 · ran · d70f04e35abd05fb
  10. GMAttendSoftmax2 helper · level 1 · ran · 9ac916d6842c5bf2
  11. GMAttendSoftmax3 helper · level 1 · ran · 7df8dd52089d875f
  12. GMAttendSoftmax4 helper · level 0 · unverified · 98e1d6884d26a55d
  13. GMAttendattention helper · level 0 · unverified · 0bb01b1fc35ef34d
  14. Siamese_Gconv helper · level 1 · ran · 8fd60000985e01f0
  15. Transformer helper · level 0 · unverified · 7d02fa050dbc4674
  16. compute_affinity helper · level 1 · ran · honoured contract · 1fc666385793ccd3
  17. match_features helper · level 1 · ran; the contract check could not run (RAISES) · 1ba154bfd017409c
  18. sinkhorn_rpm helper · level 1 · ran; the contract check could not run (RAISES) · 64cfcde03f2766ff
  19. get_graph_feature helper · level 0 · unverified · ed8b4f4d1101aff9
  20. attention helper · level 1 · ran · our draft was wrong · c032b5c8af4d2299
  21. square_distance helper · level 1 · ran; the contract check could not run (RAISES) · 4db73dd57b5d6162
  22. Gconv helper · level 1 · ran · 344c6a7217686660
  23. Decoder helper · level 1 · ran · 511f66707327f995
  24. DecoderLayer helper · level 1 · ran · 6fa6bcc8cc01f9be
  25. Encoder helper · level 1 · ran · 065e92ade1cc3217
  26. EncoderDecoder helper · level 1 · ran · 0b1c98d83e7c5bed
  27. EncoderLayer helper · level 1 · ran · 24ccd00d4adcc3a9
  28. MultiHeadedAttention helper · level 1 · ran · 16726110f1aa6e89
  29. PositionwiseFeedForward helper · level 1 · ran · 49c1ccb5ad835ec4
  30. angle helper · level 1 · ran · our draft was wrong · 4cc43825a7e3f5bc
  31. knn helper · level 1 · ran; the contract check could not run · 35d6887261f3e988
  32. LayerNorm helper · level 1 · ran · 2691a73a5c57364c
  33. clones helper · level 1 · ran · our draft was wrong · d2d810cddae9f875
  34. SublayerConnection helper · level 1 · ran · dd481d1dfb89ace0

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="2103.04256") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Graph MatchingPoint Cloud Registrationgraph construction

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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