Papers › Deep SE(3)-Equivariant Geometric Reasoning for Precise Placement Tasks

Deep SE(3)-Equivariant Geometric Reasoning for Precise Placement Tasks

20 Apr 2024arXiv:2404.13478archive 2025-07-28

Ben Eisner, Yi Yang, Todor Davchev, Mel Vecerik, Jonathan Scholz, David Held

Many robot manipulation tasks can be framed as geometric reasoning tasks, where an agent must be able to precisely manipulate an object into a position that satisfies the task from a set of initial conditions. Often, task success is defined based on the relationship between two objects - for instance, hanging a mug on a rack. In such cases, the solution should be equivariant to the initial position of the objects as well as the agent, and invariant to the pose of the camera. This poses a challenge for learning systems which attempt to solve this task by learning directly from high-dimensional demonstrations: the agent must learn to be both equivariant as well as precise, which can be challenging without any inductive biases about the problem. In this work, we propose a method for precise relative pose prediction which is provably SE(3)-equivariant, can be learned from only a few demonstrations, and can generalize across variations in a class of objects. We accomplish this by factoring the problem into learning an SE(3) invariant task-specific representation of the scene and then interpreting this representation with novel geometric reasoning layers which are provably SE(3) equivariant. We demonstrate that our method can yield substantially more precise placement predictions in simulated placement tasks than previous methods trained with the same amount of data, and can accurately represent relative placement relationships data collected from real-world demonstrations. Supplementary information and videos can be found at https://sites.google.com/view/reldist-iclr-2023.

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 22 code samples: 21 from 1 repository linked to this paper, 1 identical to code harvested from another paper's repository. Across all 22: 13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 9 unverified. Where Syntology's instrument failed: 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 21 samples from 1 repository, 12 ran (10 with no instrument failure; 2 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. 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.

r-pad/taxpose mentioned on GitHubpytorchSyntology: 21 samples, 12 ran (2 instrument-failed) · 9 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

22 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 9 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
2ran; the contract check could not run
10ran
9unverified

Licence: 1 of the 22 samples is 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 r-pad/taxpose. 1 sample is listed last, in a group without a repository. “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.

r-pad/taxpose community (archive-listed) 21 samples, 12 ran (2 instrument-failed) · 9 unverified
DGCNN in 6 papers taxpose/nets/transformer_flow.py ran MIT (permissive) · 0256b22bbf6fc0bd · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-24
Decoder in 210 papers taxpose/nets/transformer_flow.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 511f66707327f995 · report fixture: signature x:Tensor/3/float, memory:Tensor/3/float, src_mask:NoneType/0/?, tgt_mask:NoneType/0/? · returned Tensor · level recorded 2026-09-22
DecoderLayer in 43 papers taxpose/nets/transformer_flow.py ran MIT (permissive) · 6fa6bcc8cc01f9be · report fixture: signature x:Tensor/3/float, memory:Tensor/3/float, src_mask:Tensor/3/bool, tgt_mask:Tensor/3/bool · returned Tensor · level recorded 2026-09-24
Encoder in 278 papers taxpose/nets/transformer_flow.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 065e92ade1cc3217 · report fixture: signature x:Tensor/3/float, mask:NoneType/0/? · returned Tensor · level recorded 2026-09-22
EncoderDecoder taxpose/nets/transformer_flow.py ran MIT (permissive) · 0b1c98d83e7c5bed · report fixture: signature src:Tensor/2/int, tgt:Tensor/2/int, src_mask:Tensor/3/float, tgt_mask:Tensor/3/float · returned Tensor · level recorded 2026-09-24
EncoderLayer in 73 papers taxpose/nets/transformer_flow.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 24ccd00d4adcc3a9 · report fixture: signature x:Tensor/3/float, mask:NoneType/0/? · returned Tensor · level recorded 2026-09-22
MultiHeadedAttention in 38 papers taxpose/nets/transformer_flow.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 2aaa428ab3d2f019 · 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
PointNet in 5 papers taxpose/nets/transformer_flow.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 79a4b9f82b00cd47 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
PositionwiseFeedForward in 36 papers taxpose/nets/transformer_flow.py ran MIT (permissive) · 49c1ccb5ad835ec4 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-24
SublayerConnection in 16 papers taxpose/nets/transformer_flow.py ran · metamorphic tier: invariant MIT (permissive) · dd481d1dfb89ace0 · report fixture: signature x:Tensor/3/float, sublayer:callable/0/? · returned Tensor · level recorded 2026-09-22
get_graph_feature in 51 papers
census: 6 implementations from 5 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
taxpose/nets/transformer_flow.py ran; the contract check could not run (RAISES) MIT (permissive) · a4df418e59bd929e · report fixture: returned Tensor · level recorded 2026-09-22
knn in 87 papers
census: 12 implementations from 17 papers, 6 distinct outputs across 4 buckets, one shared input per bucket this sample: bucket 1 of 4, arg 1: rank 3, kind float, dtype float32
taxpose/nets/transformer_flow.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 35d6887261f3e988 · report fixture: signature x:Tensor/3/float, k:int/0/int · returned Tensor · level recorded 2026-09-22
CustomTransformer taxpose/nets/transformer_flow.py unverified MIT (permissive) · db755fe5ed8d6e0e · report
MLPKernel taxpose/nets/transformer_flow.py unverified MIT (permissive) · 06d70af2876337b8 · report
MultilaterationHead taxpose/nets/transformer_flow.py unverified MIT (permissive) · ef5dbe43a9efc444 · report
ResidualFlow_DiffEmbTransformer taxpose/nets/transformer_flow.py unverified MIT (permissive) · 8908af7a125f3b6b · report
ResidualMLPHead taxpose/nets/transformer_flow.py unverified MIT (permissive) · fe5f0050772bc142 · report
VNArgs taxpose/nets/transformer_flow.py unverified MIT (permissive) · e77d7759eb725806 · report
VN_DGCNN taxpose/nets/transformer_flow.py unverified MIT (permissive) · 9c5f4a44ab78a987 · report
create_embedding_network taxpose/nets/transformer_flow.py unverified MIT (permissive) · 97b9e03315e765bc · report
estimate_p taxpose/nets/transformer_flow.py unverified MIT (permissive) · 92c2f28b7b961ce2 · report
Repository not located 1 sample, 1 ran (0 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
attention in 144 papers
census: 11 implementations from 10 papers, 7 distinct outputs across 5 buckets, one shared input per bucket
repository not located ran · honoured contract licence of this copy not recorded · 70ba9ecc422a6a48 · report fixture: signature query:Tensor/3/float, key:Tensor/3/float, value:Tensor/3/float, mask:Tensor/4/float, dropout:callable/0/? · returned tuple · level recorded 2026-09-22

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 SE(3)-equivariant geometric reasoning method (graph method: SE(3)-equivariant geometric reasoning method). 24 bricks; individually on a fixture: 15 ran (of which 1 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 3 where Syntology's instrument failed) · 9 unverified. The assembly has not been run end-to-end.

  1. ResidualFlow_DiffEmbTransformer entry · level 0 · unverified · 8908af7a125f3b6b
  2. CustomTransformer helper · level 0 · unverified · db755fe5ed8d6e0e
  3. MultilaterationHead helper · level 0 · unverified · ef5dbe43a9efc444
  4. PointNet helper · level 1 · ran · 79a4b9f82b00cd47
  5. ResidualMLPHead model · level 0 · unverified · fe5f0050772bc142
  6. create_embedding_network helper · level 0 · unverified · 97b9e03315e765bc
  7. Decoder helper · level 1 · ran · 511f66707327f995
  8. DecoderLayer helper · level 1 · ran · 6fa6bcc8cc01f9be
  9. Encoder helper · level 1 · ran · 065e92ade1cc3217
  10. EncoderDecoder helper · level 1 · ran · 0b1c98d83e7c5bed
  11. EncoderLayer helper · level 1 · ran · 24ccd00d4adcc3a9
  12. MultiHeadedAttention helper · level 1 · ran · 2aaa428ab3d2f019
  13. PositionwiseFeedForward helper · level 1 · ran · 49c1ccb5ad835ec4
  14. MLPKernel model · level 0 · unverified · 06d70af2876337b8
  15. estimate_p helper · level 0 · unverified · 92c2f28b7b961ce2
  16. DGCNN helper · level 1 · ran · 0256b22bbf6fc0bd
  17. VNArgs helper · level 0 · unverified · e77d7759eb725806
  18. VN_DGCNN helper · level 0 · unverified · 9c5f4a44ab78a987
  19. LayerNorm helper · level 1 · ran · 2691a73a5c57364c
  20. clones helper · level 1 · ran · our draft was wrong · d2d810cddae9f875
  21. SublayerConnection helper · level 1 · ran · dd481d1dfb89ace0
  22. attention helper · level 1 · ran · honoured contract · 70ba9ecc422a6a48
  23. get_graph_feature helper · level 1 · ran; the contract check could not run (RAISES) · a4df418e59bd929e
  24. knn helper · level 1 · ran; the contract check could not run (RAISES) · 35d6887261f3e988

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="2404.13478") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Pose PredictionRobot Manipulation

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SET

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