paper-with-me

Papers

The P$^3$ dataset: Pixels, Points and Polygons for Multimodal Building Vectorization

2025-05-21 · Raphael Sulzer, Liuyun Duan, Nicolas Girard, Florent Lafarge

We present the P$^3$ dataset, a large-scale multimodal benchmark for building vectorization, constructed from aerial LiDAR point clouds, high-resolution aerial imagery, and vectorized 2D building outlines, collected across three continents. The dataset contains over 10 billion LiDAR points with decimeter-level accuracy and RGB images at a ground sampling distance of 25 centimeter. While many existing datasets primarily focus on the image modality, P$^3$ offers a complementary perspective by also incorporating dense 3D information. We demonstrate that LiDAR point clouds serve as a robust modality for predicting building polygons, both in hybrid and end-to-end learning frameworks. Moreover, fusing aerial LiDAR and imagery further improves accuracy and geometric quality of predicted polygons. The P$^3$ dataset is publicly available, along with code and pretrained weights of three state-of-the-art models for building polygon prediction at https://github.com/raphaelsulzer/PixelsPointsPolygons .

📄 PDF Abstract BibTeX arXiv:2505.15379

Code (2)

raphaelsulzer/pixelspointspolygons 공식 구현 pytorch
yeshwanth95/pix2poly pytorch

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

SuperpixelGraph: Semi-automatic generation of building footprint through semantic-sensitive superpixel and neural graph networks

2023-04-12 · Haojia Yu, Han Hu, Bo Xu, Qisen Shang 외

Most urban applications necessitate building footprints in the form of concise vector graphics with sharp boundaries rather than pixel-wise raster images. This need contrasts with the majority of existing methods, which …

SegmentationSemantic SegmentationSuperpixelsVector Graphics

PolyBuilding: Polygon Transformer for End-to-End Building Extraction

2022-11-03 · Yuan Hu, Zhibin Wang, Zhou Huang, Yu Liu

We present PolyBuilding, a fully end-to-end polygon Transformer for building extraction. PolyBuilding direct predicts vector representation of buildings from remote sensing images. It builds upon an encoder-decoder trans…

Decoder

Mining Points of Interest via Address Embeddings: An Unsupervised Approach

2021-09-09 · Abhinav Ganesan, Anubhav Gupta, Jose Mathew

Digital maps are commonly used across the globe for exploring places that users are interested in, commonly referred to as points of interest (PoI). In online food delivery platforms, PoIs could represent any major priva…

Learning Geometric Invariant Features for Classification of Vector Polygons with Graph Message-passing Neural Network

2024-07-05 · Zexian Huang, Kourosh Khoshelham, Martin Tomko

Geometric shape classification of vector polygons remains a non-trivial learning task in spatial analysis. Previous studies mainly focus on devising deep learning approaches for representation learning of rasterized vect…

Representation Learning

Roof Damage Assessment from Automated 3D Building Models

2021-06-04 · Kenichi Sugihara, Martin Wallace, Kongwen, Zhang 외

The 3D building modelling is important in urban planning and related domains that draw upon the content of 3D models of urban scenes. Such 3D models can be used to visualize city images at multiple scales from individual…