Papers › Learning Instance-Aware Correspondences for Robust Multi-Instance Point Cloud...

Learning Instance-Aware Correspondences for Robust Multi-Instance Point Cloud Registration in Cluttered Scenes

6 Apr 2024CVPR 2024 1arXiv:2404.04557archive 2025-07-28

Zhiyuan Yu, Zheng Qin, Lintao Zheng, Kai Xu

Multi-instance point cloud registration estimates the poses of multiple instances of a model point cloud in a scene point cloud. Extracting accurate point correspondence is to the center of the problem. Existing approaches usually treat the scene point cloud as a whole, overlooking the separation of instances. Therefore, point features could be easily polluted by other points from the background or different instances, leading to inaccurate correspondences oblivious to separate instances, especially in cluttered scenes. In this work, we propose MIRETR, Multi-Instance REgistration TRansformer, a coarse-to-fine approach to the extraction of instance-aware correspondences. At the coarse level, it jointly learns instance-aware superpoint features and predicts per-instance masks. With instance masks, the influence from outside of the instance being concerned is minimized, such that highly reliable superpoint correspondences can be extracted. The superpoint correspondences are then extended to instance candidates at the fine level according to the instance masks. At last, an efficient candidate selection and refinement algorithm is devised to obtain the final registrations. Extensive experiments on three public benchmarks demonstrate the efficacy of our approach. In particular, MIRETR outperforms the state of the arts by 16.6 points on F1 score on the challenging ROBI benchmark. Code and models are available at https://github.com/zhiyuanYU134/MIRETR.

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 17 code samples harvested from 1 repository linked to this paper: 14 ran (of which 4 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 6 where Syntology's instrument failed) · 3 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: 17 samples from 1 repository, 14 ran (8 with no instrument failure; 6 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.

zhiyuanyu134/miretr officialmentioned in papermentioned on GitHubpytorchSyntology: 17 samples, 14 ran (6 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

17 samples harvested: 14 ran (of which 4 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 6 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.

3ran · our draft was wrong
3ran; the contract check could not run
8ran
3unverified

Licence: 17 of the 17 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 zhiyuanyu134/miretr. “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 3 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.

zhiyuanyu134/miretr official repository 17 samples, 14 ran (6 instrument-failed) · 3 unverified
AttentionLayer in 30 papers release/robi/modules.py ran no licence file found · pointer only · 04845c3650c03509 · 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
AttentionOutput release/robi/modules.py ran no licence file found · pointer only · 6677d98e9f15a143 · report fixture: returned AttentionOutput · level recorded 2026-09-22
MonteCarloDropout release/robi/modules.py ran fingerprinted no licence file found · pointer only · cedfc23285e99bea · report fixture: returned MonteCarloDropout · 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
release/robi/modules.py ran no licence file found · pointer only · 9f1df744c0d81699 · report fixture: returned MultiHeadAttention · level recorded 2026-09-22
RPEMultiHeadAttention release/robi/modules.py ran no licence file found · pointer only · c57b8a2036045aca · report fixture: signature input_q:Tensor/3/float, input_k:Tensor/3/float, input_v:Tensor/3/float, input_p:Tensor/4/float, key_masks:NoneType/0/? · returned tuple · level recorded 2026-09-24
RPETransformerLayer release/robi/modules.py ran no licence file found · pointer only · e55bf9b5b3dc6129 · 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
SinusoidalPositionalEmbedding in 10 papers release/robi/modules.py ran fingerprinted no licence file found · pointer only · a6969607b6b2c1ef · report fixture: returned SinusoidalPositionalEmbedding · level recorded 2026-09-22
TransformerLayer in 34 papers release/robi/modules.py ran no licence file found · pointer only · 7cf0e33df6359534 · 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
cal_geodesic_vectorize release/robi/modules.py ran; the contract check could not run (RAISES) no licence file found · pointer only · c2ca71a72ccd9a5e · report fixture: signature query_points:Tensor/2/float, locs_float_:Tensor/2/float, max_step:int/0/int, neighbor:int/0/int, radius:float/0/float · returned Tensor · level recorded 2026-09-22
get_activation in 218 papers release/robi/modules.py ran · our draft was wrong no licence file found · pointer only · e8d13647b3b416c0 · report fixture: signature activation:str/0/str · returned ReLU · level recorded 2026-09-22
get_dropout release/robi/modules.py ran · our draft was wrong no licence file found · pointer only · 8629de50bd3cc48f · report fixture: signature p:float/0/float, monte_carlo_dropout:bool/0/bool · returned MonteCarloDropout · level recorded 2026-09-22
get_knn_indices release/robi/modules.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 39e05e672bb7069b · report fixture: signature points:Tensor/2/float, nodes:Tensor/2/float, k:int/0/int, return_distance:bool/0/bool · returned Tensor · level recorded 2026-09-22
pairwise_distance in 55 papers
census: 6 implementations from 7 papers, 5 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 1 of 3, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32
release/robi/modules.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 13052f545dfd4c24 · report fixture: signature points0:Tensor/2/float, points1:Tensor/2/float, normalized:bool/0/bool, clamp:bool/0/bool · returned Tensor · level recorded 2026-09-22
unique_with_inds release/robi/modules.py ran · our draft was wrong no licence file found · pointer only · 6ec42f54dda661e2 · report fixture: signature x:Tensor/2/int, dim:int/0/int · returned tuple · level recorded 2026-09-22
InstanceAwareGeoTransformer release/robi/modules.py unverified no licence file found · pointer only · 9eefb8067f51d147 · report
InstanceAwareTransformer release/robi/modules.py unverified no licence file found · pointer only · df889cd880e8f156 · report
RPEAttentionLayer release/robi/modules.py unverified no licence file found · pointer only · 5e742ab48eb26945 · 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 MIRETR (graph method: MIRETR). 17 bricks; individually on a fixture: 14 ran (of which 4 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

  1. InstanceAwareGeoTransformer entry · level 0 · unverified · 9eefb8067f51d147
  2. InstanceAwareTransformer helper · level 0 · unverified · df889cd880e8f156
  3. SinusoidalPositionalEmbedding helper · level 1 · ran · a6969607b6b2c1ef
  4. cal_geodesic_vectorize helper · level 1 · ran; the contract check could not run (RAISES) · c2ca71a72ccd9a5e
  5. get_knn_indices helper · level 1 · ran; the contract check could not run (RAISES) · 39e05e672bb7069b
  6. RPETransformerLayer helper · level 1 · ran · e55bf9b5b3dc6129
  7. TransformerLayer helper · level 1 · ran · 7cf0e33df6359534
  8. unique_with_inds helper · level 1 · ran · our draft was wrong · 6ec42f54dda661e2
  9. pairwise_distance helper · level 1 · ran; the contract check could not run (RAISES) · 13052f545dfd4c24
  10. AttentionOutput helper · level 1 · ran · 6677d98e9f15a143
  11. RPEAttentionLayer helper · level 0 · unverified · 5e742ab48eb26945
  12. AttentionLayer helper · level 1 · ran · 04845c3650c03509
  13. get_activation helper · level 1 · ran · our draft was wrong · e8d13647b3b416c0
  14. get_dropout helper · level 1 · ran · our draft was wrong · 8629de50bd3cc48f
  15. RPEMultiHeadAttention helper · level 1 · ran · c57b8a2036045aca
  16. MultiHeadAttention helper · level 1 · ran · 9f1df744c0d81699
  17. MonteCarloDropout helper · level 1 · ran · cedfc23285e99bea

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="2404.04557") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Point Cloud Registration

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