Self-Supervised Road Layout Parsing with Graph Auto-Encoding

• URL: http://arxiv.org/abs/2203.11000v1
• Date: Mon, 21 Mar 2022 14:14:26 GMT
• Title: Self-Supervised Road Layout Parsing with Graph Auto-Encoding
• Authors: Chenyang Lu, Gijs Dubbelman
• Abstract summary: We present a neural network approach that takes a road- map in bird's eye view as input, and predicts a human-interpretable graph that represents the road's topological layout. Our approach elevates the understanding of road layouts from pixel level to the level of graphs.
• Score: 5.45914480139453
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Aiming for higher-level scene understanding, this work presents a neural network approach that takes a road-layout map in bird's eye view as input, and predicts a human-interpretable graph that represents the road's topological layout. Our approach elevates the understanding of road layouts from pixel level to the level of graphs. To achieve this goal, an image-graph-image auto-encoder is utilized. The network is designed to learn to regress the graph representation at its auto-encoder bottleneck. This learning is self-supervised by an image reconstruction loss, without needing any external manual annotations. We create a synthetic dataset containing common road layout patterns and use it for training of the auto-encoder in addition to the real-world Argoverse dataset. By using this additional synthetic dataset, which conceptually captures human knowledge of road layouts and makes this available to the network for training, we are able to stabilize and further improve the performance of topological road layout understanding on the real-world Argoverse dataset. The evaluation shows that our approach exhibits comparable performance to a strong fully-supervised baseline.

Related papers

• Patch-wise Graph Contrastive Learning for Image Translation [69.85040887753729]
  We exploit the graph neural network to capture the topology-aware features. We construct the graph based on the patch-wise similarity from a pretrained encoder. In order to capture the hierarchical semantic structure, we propose the graph pooling.
  arXiv  Detail & Related papers  (2023-12-13T15:45:19Z)
• Patched Line Segment Learning for Vector Road Mapping [34.16241268436923]
  We build upon a well-defined Patched Line Segment representation for road graphs that holds geometric significance. Our method achieves state-of-the-art performance with just 6 GPU hours of training, leading to a substantial 32-fold reduction in training costs.
  arXiv  Detail & Related papers  (2023-09-06T11:33:25Z)
• GiGaMAE: Generalizable Graph Masked Autoencoder via Collaborative Latent Space Reconstruction [76.35904458027694]
  Masked autoencoder models lack good generalization ability on graph data. We propose a novel graph masked autoencoder framework called GiGaMAE. Our results will shed light on the design of foundation models on graph-structured data.
  arXiv  Detail & Related papers  (2023-08-18T16:30:51Z)
• Graph representation learning for street networks [0.0]
  Streets networks provide an invaluable source of information about the different temporal and emerging in our cities. Previous work has shown that representations of the original data can be created through a learning algorithm. This paper proposes a model capable of inferring good representations directly from the street network.
  arXiv  Detail & Related papers  (2022-11-09T16:02:28Z)
• RSG-Net: Towards Rich Sematic Relationship Prediction for Intelligent Vehicle in Complex Environments [72.04891523115535]
  We propose RSG-Net (Road Scene Graph Net): a graph convolutional network designed to predict potential semantic relationships from object proposals. The experimental results indicate that this network, trained on Road Scene Graph dataset, could efficiently predict potential semantic relationships among objects around the ego-vehicle.
  arXiv  Detail & Related papers  (2022-07-16T12:40:17Z)
• RNGDet: Road Network Graph Detection by Transformer in Aerial Images [19.141279413414082]
  Road network graphs provide critical information for autonomous vehicle applications. manually annotating road network graphs is inefficient and labor-intensive. We propose a novel approach based on transformer and imitation learning named RNGDet.
  arXiv  Detail & Related papers  (2022-02-16T01:59:41Z)
• Road Extraction from Overhead Images with Graph Neural Networks [18.649284163019516]
  We propose a method that directly infers the final road graph in a single pass. The key idea consists in combining a Fully Convolutional Network in charge of locating points of interest and a Graph Neural Network which predicts links between these points. We evaluate our method against existing works on the popular RoadTracer dataset and achieve competitive results.
  arXiv  Detail & Related papers  (2021-12-09T21:10:27Z)
• Structured Bird's-Eye-View Traffic Scene Understanding from Onboard Images [128.881857704338]
  We study the problem of extracting a directed graph representing the local road network in BEV coordinates, from a single onboard camera image. We show that the method can be extended to detect dynamic objects on the BEV plane. We validate our approach against powerful baselines and show that our network achieves superior performance.
  arXiv  Detail & Related papers  (2021-10-05T12:40:33Z)
• Image-Graph-Image Translation via Auto-Encoding [4.847617604851614]
  This work presents the first convolutional neural network that learns an image-to-graph translation task without needing external supervision. We are the first to present a self-supervised approach based on a fully-differentiable auto-encoder in which the bottleneck encodes the graph's nodes and edges.
  arXiv  Detail & Related papers  (2020-12-10T21:01:32Z)
• Road Scene Graph: A Semantic Graph-Based Scene Representation Dataset for Intelligent Vehicles [72.04891523115535]
  We propose road scene graph,a special scene-graph for intelligent vehicles. It provides not only object proposals but also their pair-wise relationships. By organizing them in a topological graph, these data are explainable, fully-connected, and could be easily processed by GCNs.
  arXiv  Detail & Related papers  (2020-11-27T07:33:11Z)
• VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation [74.56282712099274]
  This paper introduces VectorNet, a hierarchical graph neural network that exploits the spatial locality of individual road components represented by vectors. By operating on the vectorized high definition (HD) maps and agent trajectories, we avoid lossy rendering and computationally intensive ConvNet encoding steps. We evaluate VectorNet on our in-house behavior prediction benchmark and the recently released Argoverse forecasting dataset.
  arXiv  Detail & Related papers  (2020-05-08T19:07:03Z)

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.