Synthesizing Traffic Datasets using Graph Neural Networks
- URL: http://arxiv.org/abs/2312.05031v1
- Date: Fri, 8 Dec 2023 13:24:19 GMT
- Title: Synthesizing Traffic Datasets using Graph Neural Networks
- Authors: Daniel Rodriguez-Criado, Maria Chli, Luis J. Manso, George Vogiatzis
- Abstract summary: This paper introduces a novel methodology for bridging this sim-real' gap by creating photorealistic images from 2D traffic simulations and recorded junction footage.
We propose a novel image generation approach, integrating a Conditional Generative Adversarial Network with a Graph Neural Network (GNN) to facilitate the creation of realistic urban traffic images.
- Score: 2.444217495283211
- License: http://creativecommons.org/licenses/by-sa/4.0/
- Abstract: Traffic congestion in urban areas presents significant challenges, and
Intelligent Transportation Systems (ITS) have sought to address these via
automated and adaptive controls. However, these systems often struggle to
transfer simulated experiences to real-world scenarios. This paper introduces a
novel methodology for bridging this `sim-real' gap by creating photorealistic
images from 2D traffic simulations and recorded junction footage. We propose a
novel image generation approach, integrating a Conditional Generative
Adversarial Network with a Graph Neural Network (GNN) to facilitate the
creation of realistic urban traffic images. We harness GNNs' ability to process
information at different levels of abstraction alongside segmented images for
preserving locality data. The presented architecture leverages the power of
SPADE and Graph ATtention (GAT) network models to create images based on
simulated traffic scenarios. These images are conditioned by factors such as
entity positions, colors, and time of day. The uniqueness of our approach lies
in its ability to effectively translate structured and human-readable
conditions, encoded as graphs, into realistic images. This advancement
contributes to applications requiring rich traffic image datasets, from data
augmentation to urban traffic solutions. We further provide an application to
test the model's capabilities, including generating images with manually
defined positions for various entities.
Related papers
- Is Synthetic Image Useful for Transfer Learning? An Investigation into Data Generation, Volume, and Utilization [62.157627519792946]
We introduce a novel framework called bridged transfer, which initially employs synthetic images for fine-tuning a pre-trained model to improve its transferability.
We propose dataset style inversion strategy to improve the stylistic alignment between synthetic and real images.
Our proposed methods are evaluated across 10 different datasets and 5 distinct models, demonstrating consistent improvements.
arXiv Detail & Related papers (2024-03-28T22:25:05Z) - Augmented Reality based Simulated Data (ARSim) with multi-view consistency for AV perception networks [47.07188762367792]
We present ARSim, a framework designed to enhance real multi-view image data with 3D synthetic objects of interest.
We construct a simplified virtual scene using real data and strategically place 3D synthetic assets within it.
The resulting augmented multi-view consistent dataset is used to train a multi-camera perception network for autonomous vehicles.
arXiv Detail & Related papers (2024-03-22T17:49:11Z) - Building a Graph-based Deep Learning network model from captured traffic
traces [4.671648049111933]
State of the art network models are based or depend on Discrete Event Simulation (DES)
DES is highly accurate, it is also computationally costly and cumbersome to parallelize, making it unpractical to simulate high performance networks.
We propose a Graph Neural Network (GNN)-based solution specifically designed to better capture the complexities of real network scenarios.
arXiv Detail & Related papers (2023-10-18T11:16:32Z) - TransWorldNG: Traffic Simulation via Foundation Model [23.16553424318004]
We present TransWordNG, a traffic simulator that uses Data-driven algorithms and Graph Computing techniques to learn traffic dynamics from real data.
The results demonstrate that TransWorldNG can generate more realistic traffic patterns compared to traditional simulators.
arXiv Detail & Related papers (2023-05-25T05:49:30Z) - Unsupervised Domain Transfer with Conditional Invertible Neural Networks [83.90291882730925]
We propose a domain transfer approach based on conditional invertible neural networks (cINNs)
Our method inherently guarantees cycle consistency through its invertible architecture, and network training can efficiently be conducted with maximum likelihood.
Our method enables the generation of realistic spectral data and outperforms the state of the art on two downstream classification tasks.
arXiv Detail & Related papers (2023-03-17T18:00:27Z) - Unsupervised Traffic Scene Generation with Synthetic 3D Scene Graphs [83.9783063609389]
We propose a method based on domain-invariant scene representation to directly synthesize traffic scene imagery without rendering.
Specifically, we rely on synthetic scene graphs as our internal representation and introduce an unsupervised neural network architecture for realistic traffic scene synthesis.
arXiv Detail & Related papers (2023-03-15T09:26:29Z) - Attention Mechanism for Contrastive Learning in GAN-based Image-to-Image
Translation [3.90801108629495]
We propose a GAN-based model that is capable of generating high-quality images across different domains.
We leverage Contrastive Learning to train the model in a self-supervised way using image data acquired in the real world using real sensors and simulated images from 3D games.
arXiv Detail & Related papers (2023-02-23T14:23:23Z) - Street-View Image Generation from a Bird's-Eye View Layout [95.36869800896335]
Bird's-Eye View (BEV) Perception has received increasing attention in recent years.
Data-driven simulation for autonomous driving has been a focal point of recent research.
We propose BEVGen, a conditional generative model that synthesizes realistic and spatially consistent surrounding images.
arXiv Detail & Related papers (2023-01-11T18:39:34Z) - SceneGen: Learning to Generate Realistic Traffic Scenes [92.98412203941912]
We present SceneGen, a neural autoregressive model of traffic scenes that eschews the need for rules and distributions.
We demonstrate SceneGen's ability to faithfully model distributions of real traffic scenes.
arXiv Detail & Related papers (2021-01-16T22:51:43Z) - Using Simulated Data to Generate Images of Climate Change [108.43373369198765]
We explore the potential of using images from a simulated 3D environment to improve a domain adaptation task carried out by the MUNIT architecture.
We aim to use the resulting images to raise awareness of the potential future impacts of climate change.
arXiv Detail & Related papers (2020-01-26T22:19:13Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.