Papers › MG-GAN: A Multi-Generator Model Preventing Out-of-Distribution Samples in Pedestrian...

MG-GAN: A Multi-Generator Model Preventing Out-of-Distribution Samples in Pedestrian Trajectory Prediction

20 Aug 2021ICCV 2021 10arXiv:2108.09274archive 2025-07-28

Patrick Dendorfer, Sven Elflein, Laura Leal-Taixe

Pedestrian trajectory prediction is challenging due to its uncertain and multimodal nature. While generative adversarial networks can learn a distribution over future trajectories, they tend to predict out-of-distribution samples when the distribution of future trajectories is a mixture of multiple, possibly disconnected modes. To address this issue, we propose a multi-generator model for pedestrian trajectory prediction. Each generator specializes in learning a distribution over trajectories routing towards one of the primary modes in the scene, while a second network learns a categorical distribution over these generators, conditioned on the dynamics and scene input. This architecture allows us to effectively sample from specialized generators and to significantly reduce the out-of-distribution samples compared to single generator methods.

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: 10 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 4 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 16 samples from 1 repository, 10 ran (5 with no instrument failure; 5 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 on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

selflein/mg-gan officialmentioned in papermentioned on GitHubpytorchSyntology: 16 samples, 10 ran (5 instrument-failed) · 6 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: 10 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 6 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 · our draft was wrong
4ran; the contract check could not run
5ran
6unverified

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 selflein/mg-gan. “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.

selflein/mg-gan official repository 16 samples, 10 ran (5 instrument-failed) · 6 unverified
BearingMTX mggan/model/modules/discriminators.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only · d5152ea81b52bab5 · report fixture: signature x_4d:Tensor/2/float, D_4d:Tensor/3/float · returned Tensor · level recorded 2026-09-22
CNN in 23 papers mggan/model/modules/discriminators.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 8a8a07750d95c720 · report fixture: returned CNN · level recorded 2026-09-22
Conv_Blocks mggan/model/modules/discriminators.py ran · metamorphic tier: deterministic no licence file found · pointer only · ec3fed3c9fe16ca2 · report fixture: returned Conv_Blocks · level recorded 2026-09-22
DCA mggan/model/modules/discriminators.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 5373766dfa200f67 · report fixture: signature xA_4d:Tensor/1/float, xB_4d:Tensor/1/float · returned Tensor · level recorded 2026-09-22
DCA_MTX mggan/model/modules/discriminators.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 4d80b48b642ddf11 · report fixture: signature x_4d:Tensor/1/float, D_4d:Tensor/3/float · returned Tensor · level recorded 2026-09-22
EmbedSocialFeatures mggan/model/modules/discriminators.py ran · metamorphic tier: deterministic no licence file found · pointer only · 2b0dd254fdf11ea2 · report fixture: returned EmbedSocialFeatures · level recorded 2026-09-22
SocialFeatures mggan/model/modules/discriminators.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only · 9389749a263ba61c · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
TrajectoryEncoder mggan/model/modules/discriminators.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 91da0ecb8cbb8fca · report fixture: returned TrajectoryEncoder · level recorded 2026-09-22
VisualNetwork mggan/model/modules/discriminators.py ran · metamorphic tier: deterministic no licence file found · pointer only · 17bd06aa399470b5 · report fixture: returned VisualNetwork · level recorded 2026-09-22
make_mlp in 35 papers mggan/model/modules/discriminators.py ran · our draft was wrong no licence file found · pointer only · 7cef0e1b31d13120 · report fixture: signature dim_list:list/1/int, activation_list:list/1/str, batch_norm:bool/0/bool, dropout:float/0/float · returned Sequential · level recorded 2026-09-22
AttentionGlobal mggan/model/modules/discriminators.py unverified no licence file found · pointer only · ec47ec1916d71136 · report
AttentionNetwork mggan/model/modules/discriminators.py unverified no licence file found · pointer only · af19728e9d87c166 · report
AttentionPooling in 9 papers mggan/model/modules/discriminators.py unverified no licence file found · pointer only · c13ea505436bde97 · report
MultiDiscriminatorTrajectory mggan/model/modules/discriminators.py unverified no licence file found · pointer only · 5f99008b143f1d0f · report
PoolHiddenNet mggan/model/modules/discriminators.py unverified no licence file found · pointer only · bbeb758d14d2af6d · report
SocialAttention mggan/model/modules/discriminators.py unverified no licence file found · pointer only · be04a6e44d30405d · 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 MG-GAN (graph method: MG-GAN). 16 bricks; individually on a fixture: 10 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified. The assembly has not been run end-to-end.

  1. MultiDiscriminatorTrajectory entry · level 0 · unverified · 5f99008b143f1d0f
  2. AttentionGlobal helper · level 0 · unverified · ec47ec1916d71136
  3. PoolHiddenNet model · level 0 · unverified · bbeb758d14d2af6d
  4. SocialAttention helper · level 0 · unverified · be04a6e44d30405d
  5. TrajectoryEncoder helper · level 1 · ran · 91da0ecb8cbb8fca
  6. AttentionNetwork helper · level 0 · unverified · af19728e9d87c166
  7. make_mlp helper · level 1 · ran · our draft was wrong · 7cef0e1b31d13120
  8. AttentionPooling helper · level 0 · unverified · c13ea505436bde97
  9. EmbedSocialFeatures helper · level 1 · ran · 2b0dd254fdf11ea2
  10. SocialFeatures helper · level 1 · ran; the contract check could not run (RAISES) · 9389749a263ba61c
  11. VisualNetwork helper · level 1 · ran · 17bd06aa399470b5
  12. BearingMTX helper · level 1 · ran; the contract check could not run (RAISES) · d5152ea81b52bab5
  13. DCA_MTX helper · level 1 · ran; the contract check could not run (RAISES) · 4d80b48b642ddf11
  14. CNN helper · level 1 · ran · 8a8a07750d95c720
  15. DCA helper · level 1 · ran; the contract check could not run (RAISES) · 5373766dfa200f67
  16. Conv_Blocks helper · level 1 · ran · ec3fed3c9fe16ca2

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="2108.09274") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Pedestrian Trajectory PredictionTrajectory Prediction

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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