A large dataset of 100k Google Satellite and matching Map images, resembling pix2pix's Google Maps dataset.

Last update: Dec 28, 2022

Overview

Larger Google Sat2Map dataset

This dataset extends the aerial ⟷ Maps dataset used in pix2pix (Isola et al., CVPR17). The provide script download_sat2maps.py scrapes pairs of matching Maps and Satellite images using the Google Maps API from the 22 most populous cities in the United States.

Following pix2pix, the pair of satellite and map images are concatenated side-by-side into one image like below.

Occasionally, the satellite or the map image are not provided by the API, or simply not interesting like entirely water or forest. prune_out_uninteresting_regions.py prunes away these uninteresting regions using simple thresholding on the standard deviation on the color distribution of the Map images.

Using this script, an example dataset of roughly 100k images were gathered and pruned, and it can be downloaded from this link. The samples were random split into train / val set of size 92376 / 275. Since the coordinates of each image are randomly and independently sampled, it is possible that there exists overlap between the splits.

You might also like...

Official Implementation and Dataset of "PPR10K: A Large-Scale Portrait Photo Retouching Dataset with Human-Region Mask and Group-Level Consistency", CVPR 2021

Portrait Photo Retouching with PPR10K Paper | Supplementary Material PPR10K: A Large-Scale Portrait Photo Retouching Dataset with Human-Region Mask an

184 Dec 11, 2022

Code release for "COTR: Correspondence Transformer for Matching Across Images"

COTR: Correspondence Transformer for Matching Across Images This repository contains the inference code for COTR. We plan to release the training code

360 Jan 6, 2023

Space robot - (Course Project) Using the space robot to capture the target satellite that is disabled and spinning, then stabilize and fix it up

3 Jan 7, 2022

Official code for our CVPR '22 paper "Dataset Distillation by Matching Training Trajectories"

Dataset Distillation by Matching Training Trajectories Project Page | Paper This repo contains code for training expert trajectories and distilling sy

256 Jan 5, 2023

Train a deep learning net with OpenStreetMap features and satellite imagery.

DeepOSM Classify roads and features in satellite imagery, by training neural networks with OpenStreetMap (OSM) data. DeepOSM can: Download a chunk of

1.3k Nov 24, 2022

To propose and implement a multi-class classification approach to disaster assessment from the given data set of post-earthquake satellite imagery.

2 Jan 5, 2022

A vision library for performing sliced inference on large images/small objects

A large dataset of 100k Google Satellite and matching Map images, resembling pix2pix's Google Maps dataset.

Related tags

Overview

Larger Google Sat2Map dataset

You might also like...

Official Implementation and Dataset of "PPR10K: A Large-Scale Portrait Photo Retouching Dataset with Human-Region Mask and Group-Level Consistency", CVPR 2021

Code release for "COTR: Correspondence Transformer for Matching Across Images"

Space robot - (Course Project) Using the space robot to capture the target satellite that is disabled and spinning, then stabilize and fix it up

Official code for our CVPR '22 paper "Dataset Distillation by Matching Training Trajectories"

Train a deep learning net with OpenStreetMap features and satellite imagery.

To propose and implement a multi-class classification approach to disaster assessment from the given data set of post-earthquake satellite imagery.

A vision library for performing sliced inference on large images/small objects

Amazon Forest Computer Vision: Satellite Image tagging code using PyTorch / Keras with lots of PyTorch tricks

1st place solution to the Satellite Image Change Detection Challenge hosted by SenseTime

Releases(v1.0)

v1.0(Jun 20, 2021)

Owner

An Open-Source Package for Information Retrieval.

RobustART: Benchmarking Robustness on Architecture Design and Training Techniques

Alpha-IoU: A Family of Power Intersection over Union Losses for Bounding Box Regression

Implementation of OpenAI paper with Simple Noise Scale on Fastai V2

A GPU-optional modular synthesizer in pytorch, 16200x faster than realtime, for audio ML researchers.

OneShot Learning-based hotword detection.

DFFNet: An IoT-perceptive Dual Feature Fusion Network for General Real-time Semantic Segmentation

Solution of Kaggle competition: Sartorius - Cell Instance Segmentation

Implementation of Invariant Point Attention, used for coordinate refinement in the structure module of Alphafold2, as a standalone Pytorch module

DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort

A deep-learning pipeline for segmentation of ambiguous microscopic images.

Coursera - Quiz & Assignment of Coursera

Code for generating the figures in the paper "Capacity of Group-invariant Linear Readouts from Equivariant Representations: How Many Objects can be Linearly Classified Under All Possible Views?"

PyTorch implementations of the beta divergence loss.

[ICCV 2021] Focal Frequency Loss for Image Reconstruction and Synthesis

Alleviating Over-segmentation Errors by Detecting Action Boundaries

Unit-Convertor - Unit Convertor Built With Python

Morphable Detector for Object Detection on Demand

Official PyTorch implementation of BlobGAN: Spatially Disentangled Scene Representations

[ECCV 2020] Gradient-Induced Co-Saliency Detection