yeshwanth95/Pix2Poly
Official implementation of the WACV 2025 paper "Pix2Poly: A Sequence Prediction Method for End-to-end Polygonal Building Footprint Extraction from Remote Sensing Imagery".
This project helps urban planners, mappers, and GIS specialists automatically convert satellite or aerial images into precise polygonal outlines of buildings and road networks. You feed it remote sensing images, and it outputs vector graphics that clearly define the exact shape and location of structures. This is invaluable for tasks like city modeling, navigation system updates, and land use analysis.
112 stars. No commits in the last 6 months.
Use this if you need to accurately and efficiently extract detailed building footprints and road networks from satellite or aerial imagery for mapping and urban planning applications.
Not ideal if you're working with non-spatial imagery or require only general object detection rather than precise polygonal vectorization.
Stars
112
Forks
16
Language
Python
License
MIT
Category
Last pushed
Jun 05, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/yeshwanth95/Pix2Poly"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
cvg/LightGlue
LightGlue: Local Feature Matching at Light Speed (ICCV 2023)
shariqfarooq123/AdaBins
Official implementation of Adabins: Depth Estimation using adaptive bins
amusi/CVPR2026-Papers-with-Code
CVPR 2026 论文和开源项目合集
isl-org/ZoeDepth
Metric depth estimation from a single image
daviddmc/NeSVoR
NeSVoR is a package for GPU-accelerated slice-to-volume reconstruction.