Papers › Learning Multi-Scene Absolute Pose Regression with Transformers

Learning Multi-Scene Absolute Pose Regression with Transformers

21 Mar 2021ICCV 2021 10arXiv:2103.11468archive 2025-07-28

Yoli Shavit, Ron Ferens, Yosi Keller

Absolute camera pose regressors estimate the position and orientation of a camera from the captured image alone. Typically, a convolutional backbone with a multi-layer perceptron head is trained with images and pose labels to embed a single reference scene at a time. Recently, this scheme was extended for learning multiple scenes by replacing the MLP head with a set of fully connected layers. In this work, we propose to learn multi-scene absolute camera pose regression with Transformers, where encoders are used to aggregate activation maps with self-attention and decoders transform latent features and scenes encoding into candidate pose predictions. This mechanism allows our model to focus on general features that are informative for localization while embedding multiple scenes in parallel. We evaluate our method on commonly benchmarked indoor and outdoor datasets and show that it surpasses both multi-scene and state-of-the-art single-scene absolute pose regressors. We make our code publicly available from https://github.com/yolish/multi-scene-pose-transformer.

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

The archive's official repository (yolish/multi-scene-pose-transformer) was not harvested; the 20 samples below come from 1 community repository.

Syntology 20 code samples harvested from 1 repository linked to this paper: 11 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; 3 where Syntology's instrument failed) · 9 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 20 samples from 1 repository, 11 ran (8 with no instrument failure; 3 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.

yolish/multi-scene-pose-transformer officialmentioned in papermentioned on GitHubpytorchSyntology: not harvested report
yolish/c2f-ms-transformer mentioned on GitHubpytorchSyntology: 20 samples, 11 ran (3 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

20 samples harvested: 11 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; 3 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.

3ran · our draft was wrong
8ran
9unverified

Licence: 20 of the 20 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 yolish/c2f-ms-transformer. “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.

yolish/c2f-ms-transformer community (archive-listed) 20 samples, 11 ran (3 instrument-failed) · 9 unverified
BackboneBase in 5 papers models/transposenet/C2FEMSTransPoseNet.py ran · metamorphic tier: deterministic no licence file found · pointer only · 9132cb84fe26eeb2 · report fixture: returned BackboneBase · level recorded 2026-09-22
Joiner in 6 papers models/transposenet/C2FEMSTransPoseNet.py ran · metamorphic tier: deterministic no licence file found · pointer only · d90d9b6ac05da538 · report fixture: returned Joiner · level recorded 2026-09-22
PoseRegressor models/transposenet/C2FEMSTransPoseNet.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 8fa6bbba2cc99b89 · report fixture: returned PoseRegressor · level recorded 2026-09-22
PositionEmbeddingLearned in 12 papers models/transposenet/C2FEMSTransPoseNet.py ran no licence file found · pointer only · ba0bba9a80d91145 · report fixture: signature tensor_list:NestedTensor/0/? · returned Tensor · level recorded 2026-09-24
PositionEmbeddingLearnedWithPoseToken models/transposenet/C2FEMSTransPoseNet.py ran no licence file found · pointer only · aa38b878812ed339 · report fixture: signature tensor_list:NestedTensor/0/? · returned tuple · level recorded 2026-09-24
TransformerDecoder in 49 papers models/transposenet/C2FEMSTransPoseNet.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 51673b3543f0e5e1 · report fixture: returned TransformerDecoder · level recorded 2026-09-22
TransformerEncoder in 96 papers models/transposenet/C2FEMSTransPoseNet.py ran no licence file found · pointer only · e0f42697accfe894 · report fixture: signature src:Tensor/3/float, mask:NoneType/0/?, src_key_padding_mask:Tensor/2/bool, pos:Tensor/3/float · returned Tensor · level recorded 2026-09-24
TransformerEncoderLayer in 90 papers models/transposenet/C2FEMSTransPoseNet.py ran no licence file found · pointer only · e3af5e4f895771eb · report fixture: signature src:Tensor/3/float, src_mask:NoneType/0/?, src_key_padding_mask:NoneType/0/?, pos:Tensor/3/float · returned Tensor · level recorded 2026-09-24
_get_clones in 28 papers models/transposenet/C2FEMSTransPoseNet.py ran · our draft was wrong no licence file found · pointer only · e63e66b61302a7a2 · report fixture: signature module:callable/0/?, N:int/0/int · returned ModuleList · level recorded 2026-09-22
build_position_encoding in 42 papers models/transposenet/C2FEMSTransPoseNet.py ran · our draft was wrong no licence file found · pointer only · 9cbd4a5c6cc2d670 · report fixture: signature config:dict/0/? · returned PositionEmbeddingLearned · level recorded 2026-09-22
nested_tensor_from_tensor_list in 60 papers models/transposenet/C2FEMSTransPoseNet.py ran · our draft was wrong no licence file found · pointer only · a78bbd4466ce14cd · report fixture: signature tensor_list:list/1/Tensor · returned NestedTensor · level recorded 2026-09-22
Backbone in 17 papers models/transposenet/C2FEMSTransPoseNet.py unverified no licence file found · pointer only · 9428d87fe616c718 · report
C2FEMSTransPoseNet models/transposenet/C2FEMSTransPoseNet.py unverified no licence file found · pointer only · 33bd4822f730cbb3 · report
EMSTransPoseNet models/transposenet/C2FEMSTransPoseNet.py unverified no licence file found · pointer only · b05795a6da096ff6 · report
MSTransPoseNet models/transposenet/C2FEMSTransPoseNet.py unverified no licence file found · pointer only · 4dc4bf9d29572c54 · report
Transformer in 173 papers models/transposenet/C2FEMSTransPoseNet.py unverified no licence file found · pointer only · 43b8e0270ce8ecc9 · report
TransformerDecoderLayer in 45 papers models/transposenet/C2FEMSTransPoseNet.py unverified no licence file found · pointer only · 99ef5988497ebff4 · report
_onnx_nested_tensor_from_tensor_list in 9 papers models/transposenet/C2FEMSTransPoseNet.py unverified no licence file found · pointer only · 2c9ff7cc9c4634f9 · report
add_residuals models/transposenet/C2FEMSTransPoseNet.py unverified no licence file found · pointer only · cee96f998945aa8b · report
build_backbone in 29 papers models/transposenet/C2FEMSTransPoseNet.py unverified no licence file found · pointer only · 238b8ce452598dbe · 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 Learning Multi-Scene Absolute Pose Regression with Transformers (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Learning Multi-Scene Absolute Pose Regression with Transformers (graph method: Learning Multi-Scene Absolute Pose Regression with Transformers). 23 bricks; individually on a fixture: 14 ran (of which 5 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 9 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. C2FEMSTransPoseNet entry · level 0 · unverified · 33bd4822f730cbb3
  2. EMSTransPoseNet helper · level 0 · unverified · b05795a6da096ff6
  3. PoseRegressor model · level 1 · ran · 8fa6bbba2cc99b89
  4. add_residuals helper · level 0 · unverified · cee96f998945aa8b
  5. MSTransPoseNet helper · level 0 · unverified · 4dc4bf9d29572c54
  6. Transformer model · level 0 · unverified · 43b8e0270ce8ecc9
  7. build_backbone helper · level 0 · unverified · 238b8ce452598dbe
  8. nested_tensor_from_tensor_list helper · level 1 · ran · our draft was wrong · a78bbd4466ce14cd
  9. TransformerDecoder helper · level 1 · ran · 51673b3543f0e5e1
  10. TransformerDecoderLayer helper · level 0 · unverified · 99ef5988497ebff4
  11. TransformerEncoder helper · level 1 · ran · e0f42697accfe894
  12. TransformerEncoderLayer helper · level 1 · ran · e3af5e4f895771eb
  13. Backbone helper · level 0 · unverified · 9428d87fe616c718
  14. Joiner helper · level 1 · ran · d90d9b6ac05da538
  15. build_position_encoding helper · level 1 · ran · our draft was wrong · 9cbd4a5c6cc2d670
  16. NestedTensor helper · level 1 · ran · b636bcda4557023e
  17. _max_by_axis helper · level 1 · ran · honoured contract · ef393284ce3c9ea1
  18. _onnx_nested_tensor_from_tensor_list helper · level 0 · unverified · 2c9ff7cc9c4634f9
  19. _get_clones helper · level 1 · ran · our draft was wrong · e63e66b61302a7a2
  20. _get_activation_fn helper · level 1 · ran · our draft was wrong · 0bb264f52e707e08
  21. BackboneBase helper · level 1 · ran · 9132cb84fe26eeb2
  22. PositionEmbeddingLearned helper · level 1 · ran · ba0bba9a80d91145
  23. PositionEmbeddingLearnedWithPoseToken helper · level 1 · ran · aa38b878812ed339

harvested Assembly for Learning Multi-Scene Absolute Pose Regression with Transformers (graph method: Learning Multi-Scene Absolute Pose Regression with Transformers). 20 bricks; individually on a fixture: 14 ran (of which 5 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. MSTransPoseNet entry · level 0 · unverified · 4dc4bf9d29572c54
  2. PoseRegressor model · level 1 · ran · 8fa6bbba2cc99b89
  3. Transformer model · level 0 · unverified · 43b8e0270ce8ecc9
  4. build_backbone helper · level 0 · unverified · 238b8ce452598dbe
  5. nested_tensor_from_tensor_list helper · level 1 · ran · our draft was wrong · a78bbd4466ce14cd
  6. TransformerDecoder model · level 1 · ran · 51673b3543f0e5e1
  7. TransformerDecoderLayer helper · level 0 · unverified · 99ef5988497ebff4
  8. TransformerEncoder model · level 1 · ran · e0f42697accfe894
  9. TransformerEncoderLayer helper · level 1 · ran · e3af5e4f895771eb
  10. Backbone helper · level 0 · unverified · 9428d87fe616c718
  11. Joiner helper · level 1 · ran · d90d9b6ac05da538
  12. build_position_encoding helper · level 1 · ran · our draft was wrong · 9cbd4a5c6cc2d670
  13. NestedTensor helper · level 1 · ran · b636bcda4557023e
  14. _max_by_axis helper · level 1 · ran · honoured contract · ef393284ce3c9ea1
  15. _onnx_nested_tensor_from_tensor_list helper · level 0 · unverified · 2c9ff7cc9c4634f9
  16. _get_clones helper · level 1 · ran · our draft was wrong · e63e66b61302a7a2
  17. _get_activation_fn helper · level 1 · ran · our draft was wrong · 0bb264f52e707e08
  18. BackboneBase helper · level 1 · ran · 9132cb84fe26eeb2
  19. PositionEmbeddingLearned helper · level 1 · ran · ba0bba9a80d91145
  20. PositionEmbeddingLearnedWithPoseToken helper · level 1 · ran · aa38b878812ed339

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="2103.11468") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Visual Localizationregression

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Visual Localization Oxford Radar RobotCar (Full-6) MS-Transformer Mean Translation Error 11.69 #9 of 16 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