Papers › Multiview Scene Graph

Multiview Scene Graph

15 Oct 2024arXiv:2410.11187archive 2025-07-28

Juexiao Zhang, Gao Zhu, Sihang Li, Xinhao Liu, Haorui Song, Xinran Tang, Chen Feng

A proper scene representation is central to the pursuit of spatial intelligence where agents can robustly reconstruct and efficiently understand 3D scenes. A scene representation is either metric, such as landmark maps in 3D reconstruction, 3D bounding boxes in object detection, or voxel grids in occupancy prediction, or topological, such as pose graphs with loop closures in SLAM or visibility graphs in SfM. In this work, we propose to build Multiview Scene Graphs (MSG) from unposed images, representing a scene topologically with interconnected place and object nodes. The task of building MSG is challenging for existing representation learning methods since it needs to jointly address both visual place recognition, object detection, and object association from images with limited fields of view and potentially large viewpoint changes. To evaluate any method tackling this task, we developed an MSG dataset and annotation based on a public 3D dataset. We also propose an evaluation metric based on the intersection-over-union score of MSG edges. Moreover, we develop a novel baseline method built on mainstream pretrained vision models, combining visual place recognition and object association into one Transformer decoder architecture. Experiments demonstrate that our method has superior performance compared to existing relevant baselines.

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 37 code samples harvested from 1 repository linked to this paper: 17 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; 6 where Syntology's instrument failed) · 20 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 37 samples from 1 repository, 17 ran (11 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.

ai4ce/MSG officialmentioned on GitHubpytorchSyntology: 37 samples, 17 ran (6 instrument-failed) · 20 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

37 samples harvested: 17 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; 6 where Syntology's instrument failed) · 20 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
5ran · our draft was wrong
1ran; the contract check could not run
10ran
20unverified

Licence: 37 of the 37 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 ai4ce/MSG. “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.

ai4ce/MSG official repository 37 samples, 17 ran (6 instrument-failed) · 20 unverified
ConvNextBase_Embedder models/msg.py ran · our draft was wrong no licence file found · pointer only · 40d84dc597dc5b1c · report fixture: signature output_type:str/0/str, freeze:bool/0/bool, weights:NoneType/0/? · returned ConvNextEmbedder · level recorded 2026-09-22
ConvNextEmbedder models/msg.py ran no licence file found · pointer only · 752a360f7b9eb85f · report fixture: signature pixel_values:Tensor/4/float · returned Tensor · level recorded 2026-09-24
ConvNextSmall_Embedder models/msg.py ran · our draft was wrong no licence file found · pointer only · 54fcc84b102bad86 · report fixture: signature output_type:str/0/str, freeze:bool/0/bool, weights:NoneType/0/? · returned ConvNextEmbedder · level recorded 2026-09-22
FocalLoss in 9 papers models/msg.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · f67fa56df1c59beb · report fixture: signature predictions:Tensor/2/float, supervision:Tensor/2/float, mask:Tensor/2/float · returned Tensor · level recorded 2026-09-22
HungarianMatcher in 5 papers models/msg.py ran · metamorphic tier: deterministic no licence file found · pointer only · 819c547304b8a327 · report fixture: signature outputs:list/1/dict, targets:list/1/dict · returned list · level recorded 2026-09-22
InfoNCELoss models/msg.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 1b5e70ab90b23040 · report fixture: signature predictions:Tensor/2/float, supervision_matrix_masked:Tensor/2/float, mask:Tensor/2/float · returned Tensor · level recorded 2026-09-22
MaskBCELoss models/msg.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 95aa1e31d129e66d · report fixture: signature predictions:Tensor/2/float, supervision:Tensor/2/float, mask:Tensor/2/float · returned Tensor · level recorded 2026-09-22
MaskMetricLoss models/msg.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · ab5d728836f0b4c4 · report fixture: signature predictions:Tensor/2/float, supervision:Tensor/2/float, mask:Tensor/2/float · returned Tensor · level recorded 2026-09-22
MeanSimilarityLoss models/msg.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · b54a9a499b60193c · report fixture: signature embeddings:Tensor/2/float, flatten_idx:Tensor/1/int · returned tuple · level recorded 2026-09-22
ResNetEmbedder models/msg.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · fd0abe8d08081f03 · report fixture: signature pixel_values:Tensor/4/float · returned Tensor · level recorded 2026-09-22
TotalCodingRate models/msg.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 5e019a64f1ed0584 · report fixture: signature embeddings:Tensor/2/float, idx:Tensor/1/int · returned Tensor · level recorded 2026-09-22
ViTHuge_Embedder models/msg.py ran no licence file found · pointer only · bf7da5b09d43fb50 · report fixture: returned ViTEmbedder · level recorded 2026-09-22
convert_detections models/msg.py ran · our draft was wrong no licence file found · pointer only · 3bd3f22093889b54 · report fixture: signature info:dict/0/? · returned list · level recorded 2026-09-22
enlarge_boxes models/msg.py ran; the contract check could not run (RAISES) no licence file found · pointer only · dedae867c2c8f17c · report fixture: signature boxes:Tensor/2/float, image_size:tuple/1/int, scale:float/0/float · returned Tensor · level recorded 2026-09-22
get_association_sv models/msg.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 32c260519d129307 · report fixture: signature total_reorderd_indx:Tensor/1/int · returned tuple · level recorded 2026-09-22
get_match_idx models/msg.py ran · honoured contract no licence file found · pointer only · b2650b36fe58513c · report fixture: signature match_indices:list/1/tuple, info:dict/0/?, N:int/0/int · returned Tensor · level recorded 2026-09-22
random_shift_boxes models/msg.py ran · our draft was wrong no licence file found · pointer only · a39c8336c18c37bd · report fixture: signature bboxes:Tensor/2/float, image_size:tuple/1/int, shift_ratio:float/0/float · returned Tensor · level recorded 2026-09-22
AoMSG_B_4 models/msg.py unverified no licence file found · pointer only · 69a9f42147bf8797 · report
AoMSG_S_1 models/msg.py unverified no licence file found · pointer only · 25f90b846466d545 · report
AoMSG_S_2 models/msg.py unverified no licence file found · pointer only · de182360d20cdaf0 · report
AoMSG_S_4 models/msg.py unverified no licence file found · pointer only · 934a836dc53d690c · report
ConvNextTiny_Embedder models/msg.py unverified no licence file found · pointer only · e3527da9eef2f19b · report
DINOv2Base_Embedder models/msg.py unverified no licence file found · pointer only · 863c2f1d94fe349a · report
DINOv2Embedder models/msg.py unverified no licence file found · pointer only · 05b9d0739db60f02 · report
DINOv2Large_Embedder models/msg.py unverified no licence file found · pointer only · e836ef8016b3a473 · report
DINOv2Small_Embedder models/msg.py unverified no licence file found · pointer only · 457e9b8995e57db6 · report
DecoderAssociator models/msg.py unverified no licence file found · pointer only · ca68d06b734a44d5 · report
MSGer models/msg.py unverified no licence file found · pointer only · adf48445a6791bb9 · report
ResNet18_Embedder models/msg.py unverified no licence file found · pointer only · 8e2488b11e5fd27e · report
ResNet50_Embedder models/msg.py unverified no licence file found · pointer only · a93fec62fb9e9db9 · report
SepAssociator models/msg.py unverified no licence file found · pointer only · 3ec9dfaa5c5b8e6e · report
SepMSG_direct models/msg.py unverified no licence file found · pointer only · 65ca232f872e5782 · report
SepMSG_linear models/msg.py unverified no licence file found · pointer only · d75eb66f45ffc404 · report
SepMSG_mlp models/msg.py unverified no licence file found · pointer only · 3fac03cf157f4a28 · report
ViTBase_Embedder models/msg.py unverified no licence file found · pointer only · ca176d4fcf9648e9 · report
ViTEmbedder models/msg.py unverified no licence file found · pointer only · c77826532de67d46 · report
ViTLarge_Embedder models/msg.py unverified no licence file found · pointer only · de30c5ad7d5334a0 · 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 Multiview Scene Graphs (graph method: Multiview Scene Graphs). 43 bricks; individually on a fixture: 22 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 3 honoured, 0 violated, 10 with no contract checked; 9 where Syntology's instrument failed) · 21 unverified. The assembly has not been run end-to-end.

  1. MSGer entry · level 0 · unverified · adf48445a6791bb9
  2. HungarianMatcher helper · level 1 · ran · 819c547304b8a327
  3. convert_detections data_transform · level 1 · ran · our draft was wrong · 3bd3f22093889b54
  4. enlarge_boxes helper · level 1 · ran; the contract check could not run (RAISES) · dedae867c2c8f17c
  5. random_shift_boxes helper · level 1 · ran · our draft was wrong · a39c8336c18c37bd
  6. generalized_box_iou helper · level 1 · ran; the contract check could not run · dc8fb9b6fb48ac37
  7. box_iou helper · level 1 · ran · honoured contract · ce749f837424dd8c
  8. AoMSG_B_4 helper · level 0 · unverified · 69a9f42147bf8797
  9. AoMSG_S_1 helper · level 0 · unverified · 25f90b846466d545
  10. AoMSG_S_2 helper · level 0 · unverified · de182360d20cdaf0
  11. AoMSG_S_4 helper · level 0 · unverified · 934a836dc53d690c
  12. ConvNextBase_Embedder helper · level 1 · ran · our draft was wrong · 40d84dc597dc5b1c
  13. ConvNextEmbedder model · level 1 · ran · 752a360f7b9eb85f
  14. ConvNextSmall_Embedder helper · level 1 · ran · our draft was wrong · 54fcc84b102bad86
  15. ConvNextTiny_Embedder helper · level 0 · unverified · e3527da9eef2f19b
  16. DINOv2Base_Embedder helper · level 0 · unverified · 863c2f1d94fe349a
  17. DINOv2Embedder model · level 0 · unverified · 05b9d0739db60f02
  18. DINOv2Large_Embedder helper · level 0 · unverified · e836ef8016b3a473
  19. DINOv2Small_Embedder helper · level 0 · unverified · 457e9b8995e57db6
  20. DecoderAssociator helper · level 0 · unverified · ca68d06b734a44d5
  21. FocalLoss loss · level 1 · ran · f67fa56df1c59beb
  22. InfoNCELoss loss · level 1 · ran · 1b5e70ab90b23040
  23. MaskBCELoss loss · level 1 · ran · 95aa1e31d129e66d
  24. MaskMetricLoss loss · level 1 · ran · ab5d728836f0b4c4
  25. MeanSimilarityLoss helper · level 1 · ran · b54a9a499b60193c
  26. ResNet18_Embedder helper · level 0 · unverified · 8e2488b11e5fd27e
  27. ResNet50_Embedder helper · level 0 · unverified · a93fec62fb9e9db9
  28. ResNetEmbedder model · level 1 · ran · fd0abe8d08081f03
  29. SepAssociator helper · level 0 · unverified · 3ec9dfaa5c5b8e6e
  30. SepMSG_direct helper · level 0 · unverified · 65ca232f872e5782
  31. SepMSG_linear helper · level 0 · unverified · d75eb66f45ffc404
  32. SepMSG_mlp helper · level 0 · unverified · 3fac03cf157f4a28
  33. TotalCodingRate helper · level 1 · ran · 5e019a64f1ed0584
  34. ViTBase_Embedder helper · level 0 · unverified · ca176d4fcf9648e9
  35. ViTEmbedder model · level 0 · unverified · c77826532de67d46
  36. ViTHuge_Embedder helper · level 1 · ran · bf7da5b09d43fb50
  37. ViTLarge_Embedder helper · level 0 · unverified · de30c5ad7d5334a0
  38. get_1d_sincos_pos_embed_from_grid helper · level 1 · ran; the contract check could not run · 5c8ea92d43ead77d
  39. get_2d_sincos_pos_embed helper · level 1 · ran · honoured contract · 5a37690a13a6157d
  40. get_2d_sincos_pos_embed_from_grid helper · level 0 · unverified · 2884deadbb637c3e
  41. get_association_sv helper · level 1 · ran · our draft was wrong · 32c260519d129307
  42. get_match_idx helper · level 1 · ran · honoured contract · b2650b36fe58513c
  43. off_diagonal helper · level 1 · ran; the contract check could not run · 3e30d88eaef01190

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="2410.11187") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

DecoderObjectObject DetectionRepresentation LearningVisual Place Recognitionobject-detection

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