Papers › Text2Pos: Text-to-Point-Cloud Cross-Modal Localization

Text2Pos: Text-to-Point-Cloud Cross-Modal Localization

28 Mar 2022CVPR 2022 1arXiv:2203.15125archive 2025-07-28

Manuel Kolmet, Qunjie Zhou, Aljosa Osep, Laura Leal-Taixe

Natural language-based communication with mobile devices and home appliances is becoming increasingly popular and has the potential to become natural for communicating with mobile robots in the future. Towards this goal, we investigate cross-modal text-to-point-cloud localization that will allow us to specify, for example, a vehicle pick-up or goods delivery location. In particular, we propose Text2Pos, a cross-modal localization module that learns to align textual descriptions with localization cues in a coarse- to-fine manner. Given a point cloud of the environment, Text2Pos locates a position that is specified via a natural language-based description of the immediate surroundings. To train Text2Pos and study its performance, we construct KITTI360Pose, the first dataset for this task based on the recently introduced KITTI360 dataset. Our experiments show that we can localize 65% of textual queries within 15m distance to query locations for top-10 retrieved locations. This is a starting point that we hope will spark future developments towards language-based navigation.

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 16 code samples harvested from 1 repository linked to this paper: 9 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 7 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): 16 samples from 1 repository, 9 ran (7 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.

CV4RA/MambaPlace mentioned on GitHubpytorchSyntology: not harvested report
kevin301342/cmmloc mentioned on GitHubpytorchSyntology: 16 samples, 9 ran (2 instrument-failed) · 7 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

16 samples harvested: 9 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 7 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.

2ran; the contract check could not run
7ran
7unverified

Licence: 16 of the 16 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 kevin301342/cmmloc. “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.

kevin301342/cmmloc community (archive-listed) 16 samples, 9 ran (2 instrument-failed) · 7 unverified
BertSelfAttention in 29 papers models/coarse/cell_retrieval.py ran no licence file found · pointer only · 9a383ff97b1c44e8 · report fixture: signature query_states:Tensor/3/float, key_states:Tensor/3/float, value_states:Tensor/3/float, attention_mask:Tensor/3/float · returned Tensor · level recorded 2026-09-24
FeedForward in 198 papers models/coarse/cell_retrieval.py ran · metamorphic tier: deterministic no licence file found · pointer only · 618350b6cee00b41 · report fixture: returned FeedForward · level recorded 2026-09-22
GlobalAbstractionLayer models/coarse/cell_retrieval.py ran · metamorphic tier: deterministic no licence file found · pointer only · 77aad13bfc87c6a9 · report fixture: returned GlobalAbstractionLayer · level recorded 2026-09-22
LinearLayer in 14 papers models/coarse/cell_retrieval.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 3df8c1fd92a5fb57 · report fixture: returned LinearLayer · level recorded 2026-09-22
Object3d models/coarse/cell_retrieval.py ran · metamorphic tier: deterministic no licence file found · pointer only · d8915d0cc32534bb · report fixture: returned Object3d · level recorded 2026-09-22
SetAbstractionLayer models/coarse/cell_retrieval.py ran · metamorphic tier: deterministic no licence file found · pointer only · 739374c49764ce07 · report fixture: returned SetAbstractionLayer · level recorded 2026-09-22
TrainablePositionalEncoding models/coarse/cell_retrieval.py ran · metamorphic tier: deterministic no licence file found · pointer only · 12725df1d639640b · report fixture: returned TrainablePositionalEncoding · level recorded 2026-09-22
get_mlp in 15 papers models/coarse/cell_retrieval.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic no licence file found · pointer only · 18a5e06ec868fe4d · report fixture: signature channels:list/1/int, add_batchnorm:bool/0/bool · returned Sequential · level recorded 2026-09-22
get_mlp2 models/coarse/cell_retrieval.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic no licence file found · pointer only · 193deb6b7751d2db · report fixture: signature channels:list/1/int, add_batchnorm:bool/0/bool · returned Sequential · level recorded 2026-09-22
BertAttention in 28 papers models/coarse/cell_retrieval.py unverified no licence file found · pointer only · 565f1b7b15ab3e88 · report
BertCrossAttention models/coarse/cell_retrieval.py unverified no licence file found · pointer only · 4fcfefebb4e7bed6 · report
CMMT_SC models/coarse/cell_retrieval.py unverified no licence file found · pointer only · 39f05e08caaa08a5 · report
CellRetrievalNetwork models/coarse/cell_retrieval.py unverified no licence file found · pointer only · 8aa1196dc8c83c16 · report
LanguageEncoder models/coarse/cell_retrieval.py unverified no licence file found · pointer only · d5aa347b6fc56515 · report
ObjectEncoder models/coarse/cell_retrieval.py unverified no licence file found · pointer only · 398965e9268b7a43 · report
PointNet2 models/coarse/cell_retrieval.py unverified no licence file found · pointer only · 82bdfc486f8ff8dc · 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 Text2Pos (graph method: Text2Pos). 16 bricks; individually on a fixture: 9 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified. The assembly has not been run end-to-end.

  1. CellRetrievalNetwork entry · level 0 · unverified · 8aa1196dc8c83c16
  2. CMMT_SC model · level 0 · unverified · 39f05e08caaa08a5
  3. LanguageEncoder helper · level 0 · unverified · d5aa347b6fc56515
  4. LinearLayer helper · level 1 · ran · 3df8c1fd92a5fb57
  5. ObjectEncoder helper · level 0 · unverified · 398965e9268b7a43
  6. TrainablePositionalEncoding helper · level 1 · ran · 12725df1d639640b
  7. BertAttention model · level 0 · unverified · 565f1b7b15ab3e88
  8. BertCrossAttention model · level 0 · unverified · 4fcfefebb4e7bed6
  9. get_mlp2 helper · level 1 · ran; the contract check could not run (RAISES) · 193deb6b7751d2db
  10. Object3d helper · level 1 · ran · d8915d0cc32534bb
  11. PointNet2 helper · level 0 · unverified · 82bdfc486f8ff8dc
  12. get_mlp helper · level 1 · ran; the contract check could not run (RAISES) · 18a5e06ec868fe4d
  13. BertSelfAttention model · level 1 · ran · 9a383ff97b1c44e8
  14. FeedForward helper · level 1 · ran · 618350b6cee00b41
  15. GlobalAbstractionLayer helper · level 1 · ran · 77aad13bfc87c6a9
  16. SetAbstractionLayer helper · level 1 · ran · 739374c49764ce07

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="2203.15125") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Visual Place Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Visual Place Recognition KITTI360pose Text2Pos Localization Recall@1 0.14 #5 of 5 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

ALIGN

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