SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2108.09274 · ICCV · 2021

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

Sven Elflein, Patrick Dendorfer

arXiv · PDF · Open in the Atlas

Code that ran

10 of 16 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (5 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 5 have no contract verdict; 5 failures of our instrument; 6 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2108.09274.json · badge: /api/ran/2108.09274.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
selflein/MG-GAN community
Papers with Code archive
10 ran · 6 no recorded run
FunctionStatusWhere it lives
BearingMTX Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
selflein/MG-GAN/mggan/model/modules/discriminators.py
pointer only (licence: NONE) · get_code("d5152ea81b52bab5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, selflein/MG-GAN when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

CNN Ran
ran on a synthesized input · constructed an object; no result was computed
selflein/MG-GAN/mggan/model/modules/discriminators.py
pointer only (licence: NONE) · get_code("8a8a07750d95c720")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, selflein/MG-GAN when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Conv_Blocks Ran
ran on a synthesized input · constructed an object; no result was computed
selflein/MG-GAN/mggan/model/modules/discriminators.py
pointer only (licence: NONE) · get_code("ec3fed3c9fe16ca2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, selflein/MG-GAN when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

DCA Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
selflein/MG-GAN/mggan/model/modules/discriminators.py
pointer only (licence: NONE) · get_code("5373766dfa200f67")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, selflein/MG-GAN when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

DCA_MTX Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
selflein/MG-GAN/mggan/model/modules/discriminators.py
pointer only (licence: NONE) · get_code("4d80b48b642ddf11")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, selflein/MG-GAN when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

EmbedSocialFeatures Ran
ran on a synthesized input · constructed an object; no result was computed
selflein/MG-GAN/mggan/model/modules/discriminators.py
pointer only (licence: NONE) · get_code("2b0dd254fdf11ea2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, selflein/MG-GAN when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

SocialFeatures Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
selflein/MG-GAN/mggan/model/modules/discriminators.py
pointer only (licence: NONE) · get_code("9389749a263ba61c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, selflein/MG-GAN when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

TrajectoryEncoder Ran
ran on a synthesized input · constructed an object; no result was computed
selflein/MG-GAN/mggan/model/modules/discriminators.py
pointer only (licence: NONE) · get_code("91da0ecb8cbb8fca")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, selflein/MG-GAN when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

VisualNetwork Ran
ran on a synthesized input · constructed an object; no result was computed
selflein/MG-GAN/mggan/model/modules/discriminators.py
pointer only (licence: NONE) · get_code("17bd06aa399470b5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, selflein/MG-GAN when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

make_mlp Ran
ran; our contract draft was wrong, not the code
selflein/MG-GAN/mggan/model/modules/discriminators.py
pointer only (licence: NONE) · get_code("7cef0e1b31d13120")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, selflein/MG-GAN when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

AttentionGlobal Not yet run
unverified (harvested, no recorded run)
selflein/MG-GAN/mggan/model/modules/discriminators.py
pointer only (licence: NONE) · get_code("ec47ec1916d71136")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, selflein/MG-GAN when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

AttentionNetwork Not yet run
unverified (harvested, no recorded run)
selflein/MG-GAN/mggan/model/modules/discriminators.py
pointer only (licence: NONE) · get_code("af19728e9d87c166")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, selflein/MG-GAN when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

AttentionPooling Not yet run
unverified (harvested, no recorded run)
selflein/MG-GAN/mggan/model/modules/discriminators.py
pointer only (licence: NONE) · get_code("c13ea505436bde97")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, selflein/MG-GAN when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

MultiDiscriminatorTrajectory Not yet run
unverified (harvested, no recorded run)
selflein/MG-GAN/mggan/model/modules/discriminators.py
pointer only (licence: NONE) · get_code("5f99008b143f1d0f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, selflein/MG-GAN when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

PoolHiddenNet Not yet run
unverified (harvested, no recorded run)
selflein/MG-GAN/mggan/model/modules/discriminators.py
pointer only (licence: NONE) · get_code("bbeb758d14d2af6d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, selflein/MG-GAN when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

SocialAttention Not yet run
unverified (harvested, no recorded run)
selflein/MG-GAN/mggan/model/modules/discriminators.py
pointer only (licence: NONE) · get_code("be04a6e44d30405d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, selflein/MG-GAN when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 later) and 15 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
make_mlp
brick of this paper's assembly: helper
1 other paper
1 dated earlier
2010.01114 (2020-10)
Goal-GAN: Multimodal Trajectory Prediction Based on Goal Position Estimation

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2108.09274")
get_code_for_paper("2108.09274")
have("2108.09274")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2108.09274.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2108.09274.svg)](https://syntology.ai/paper/2108.09274)

Connect an agent — have() is free.