Papers › MiKASA: Multi-Key-Anchor & Scene-Aware Transformer for 3D Visual Grounding

MiKASA: Multi-Key-Anchor & Scene-Aware Transformer for 3D Visual Grounding

5 Mar 2024CVPR 2024 1arXiv:2403.03077archive 2025-07-28

Chun-Peng Chang, Shaoxiang Wang, Alain Pagani, Didier Stricker

3D visual grounding involves matching natural language descriptions with their corresponding objects in 3D spaces. Existing methods often face challenges with accuracy in object recognition and struggle in interpreting complex linguistic queries, particularly with descriptions that involve multiple anchors or are view-dependent. In response, we present the MiKASA (Multi-Key-Anchor Scene-Aware) Transformer. Our novel end-to-end trained model integrates a self-attention-based scene-aware object encoder and an original multi-key-anchor technique, enhancing object recognition accuracy and the understanding of spatial relationships. Furthermore, MiKASA improves the explainability of decision-making, facilitating error diagnosis. Our model achieves the highest overall accuracy in the Referit3D challenge for both the Sr3D and Nr3D datasets, particularly excelling by a large margin in categories that require viewpoint-dependent descriptions.

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: 11 ran (of which 10 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 16 samples from 1 repository, 11 ran (11 with no instrument failure; 0 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.

dfki-av/mikasa-3dvg officialmentioned in paperpytorchSyntology: 16 samples, 11 ran (0 instrument-failed) · 5 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: 11 ran (of which 10 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 5 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.

11ran
5unverified

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 dfki-av/mikasa-3dvg. “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 6 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.

dfki-av/mikasa-3dvg official repository 16 samples, 11 ran (0 instrument-failed) · 5 unverified
BatchNorm2d in 9 papers models/MiKASA_transformer.py ran no licence file found · pointer only · c9ea4b32ab8ee01d · report fixture: returned BatchNorm2d · level recorded 2026-09-22
Conv2d in 43 papers
census: 7 implementations from 7 papers, 6 distinct outputs on one shared input
models/MiKASA_transformer.py ran fingerprinted no licence file found · pointer only · 43954295982678e1 · report fixture: returned Conv2d · level recorded 2026-09-22
CrossFFN models/MiKASA_transformer.py ran no licence file found · pointer only · a2c9643fb81b1320 · report fixture: returned CrossFFN · level recorded 2026-09-22
FeedForwardLayer in 9 papers models/MiKASA_transformer.py ran no licence file found · pointer only · 7eb05f38c1da0278 · report fixture: returned FeedForwardLayer · level recorded 2026-09-22
FusionNet in 5 papers models/MiKASA_transformer.py ran no licence file found · pointer only · fbfaf9b85641a7d4 · report fixture: returned FusionNet · level recorded 2026-09-22
GroupAll models/MiKASA_transformer.py ran no licence file found · pointer only · d0c66f6eec198b93 · report fixture: signature xyz:Tensor/3/float, new_xyz:Tensor/3/float, features:Tensor/3/float · returned Tensor · level recorded 2026-09-24
MultiHeadSpatialNet models/MiKASA_transformer.py ran no licence file found · pointer only · c6818d25fb38e40e · report fixture: returned MultiHeadSpatialNet · level recorded 2026-09-22
QueryAndGroup models/MiKASA_transformer.py ran no licence file found · pointer only · 79ba2e730dfd23fc · report fixture: returned QueryAndGroup · level recorded 2026-09-22
SharedMLP in 7 papers models/MiKASA_transformer.py ran no licence file found · pointer only · ce88d757651269ea · report fixture: returned SharedMLP · level recorded 2026-09-22
_BNBase models/MiKASA_transformer.py ran fingerprinted no licence file found · pointer only · f3c2a0236652d30c · report fixture: returned _BNBase · level recorded 2026-09-22
_ConvBase models/MiKASA_transformer.py ran fingerprinted no licence file found · pointer only · 29953e9c8508d4e0 · report fixture: returned _ConvBase · level recorded 2026-09-22
MiKASA_transformer models/MiKASA_transformer.py unverified no licence file found · pointer only · 234728b3b9078cf1 · report
PointNetPP models/MiKASA_transformer.py unverified no licence file found · pointer only · 7225d8c84c7f69c2 · report
PointnetSAModuleMSG in 9 papers models/MiKASA_transformer.py unverified no licence file found · pointer only · 644b83bc52ec1cc1 · report
_PointnetSAModuleBase in 8 papers models/MiKASA_transformer.py unverified no licence file found · pointer only · a7de4c208ca1025c · report
break_up_pc models/MiKASA_transformer.py unverified no licence file found · pointer only · 775337099d9f9b3c · 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 MiKASA (graph method: MiKASA). 20 bricks; individually on a fixture: 15 ran (of which 14 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

  1. MiKASA_transformer entry · level 0 · unverified · 234728b3b9078cf1
  2. FusionNet model · level 1 · ran · fbfaf9b85641a7d4
  3. PointNetPP helper · level 0 · unverified · 7225d8c84c7f69c2
  4. CrossFFN model · level 1 · ran · a2c9643fb81b1320
  5. MultiHeadSpatialNet model · level 1 · ran · c6818d25fb38e40e
  6. PointnetSAModuleMSG helper · level 0 · unverified · 644b83bc52ec1cc1
  7. break_up_pc helper · level 0 · unverified · 775337099d9f9b3c
  8. FeedForwardLayer model · level 1 · ran · 7eb05f38c1da0278
  9. GroupAll helper · level 1 · ran · d0c66f6eec198b93
  10. QueryAndGroup helper · level 1 · ran · 79ba2e730dfd23fc
  11. SharedMLP helper · level 1 · ran · ce88d757651269ea
  12. _PointnetSAModuleBase helper · level 0 · unverified · a7de4c208ca1025c
  13. Conv2d helper · level 1 · ran · 43954295982678e1
  14. BatchNorm2d helper · level 1 · ran · c9ea4b32ab8ee01d
  15. _ConvBase helper · level 1 · ran · 29953e9c8508d4e0
  16. _BNBase helper · level 1 · ran · f3c2a0236652d30c
  17. BallQuery helper · level 1 · ran · fb26ce705d6a2cb9
  18. FurthestPointSampling helper · level 1 · ran · f038cc7c8955a963
  19. GatherOperation helper · level 1 · ran · 3c75be14968690dc
  20. GroupingOperation helper · level 1 · ran · 4d80a2b4a0fba485

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="2403.03077") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

3D visual groundingDecision MakingObjectObject RecognitionVisual Grounding

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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