paper-with-me

홈 › Papers

Self-Supervised Road Layout Parsing with Graph Auto-Encoding

2022-03-21 · Chenyang Lu, Gijs Dubbelman

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.

📄 PDF Abstract BibTeX arXiv:2203.11000

Code (1)

tue-mps/road-as-graph 공식 구현 pytorch

Tasks

Image ReconstructionScene Understanding

Similar Papers 제목 키워드 기반

Infinity Parser: Layout Aware Reinforcement Learning for Scanned Document Parsing

2025-10-17 · Baode Wang, Biao Wu, Weizhen Li, Meng Fang 외 arxiv

Document parsing from scanned images into structured formats remains a significant challenge due to its complexly intertwined elements such as text paragraphs, figures, formulas, and tables. Existing supervised fine-tuni…

Reinforcement Learning

Neural Turtle Graphics for Modeling City Road Layouts

2019-10-04 · ICCV 2019 10 · Hang Chu, Daiqing Li, David Acuna, Amlan Kar 외

We propose Neural Turtle Graphics (NTG), a novel generative model for spatial graphs, and demonstrate its applications in modeling city road layouts. Specifically, we represent the road layout using a graph where nodes i…

Self-supervised Photographic Image Layout Representation Learning

2024-03-06 · Zhaoran Zhao, Peng Lu, Xujun Peng, Wenhao Guo

In the domain of image layout representation learning, the critical process of translating image layouts into succinct vector forms is increasingly significant across diverse applications, such as image retrieval, manipu…

Image RetrievalRepresentation LearningSelf-Supervised Learning

Learning a Model for Inferring a Spatial Road Lane Network Graph using Self-Supervision

2021-07-05 · Robin Karlsson, David Robert Wong, Simon Thompson, Kazuya Takeda

Interconnected road lanes are a central concept for navigating urban roads. Currently, most autonomous vehicles rely on preconstructed lane maps as designing an algorithmic model is difficult. However, the generation and…

Autonomous VehiclesSelf-Supervised Learning

Dolphin-v2: Universal Document Parsing via Scalable Anchor Prompting

2026-02-05 · Hao Feng, Wei Shi, Ke Zhang, Xiang Fei 외 arxiv

Document parsing has garnered widespread attention as vision-language models (VLMs) advance OCR capabilities. However, the field remains fragmented across dozens of specialized models with varying strengths, forcing user…

Attribute Extraction