• Publications
  • Influence
Wide-Area Image Geolocalization with Aerial Reference Imagery
TLDR
We propose to use deep convolutional neural networks to address the problem of cross-view image geolocalization, in which the geolocation of a ground-level query image is estimated by matching to georeferenced aerial images. Expand
  • 111
  • 20
  • PDF
Predicting Ground-Level Scene Layout from Aerial Imagery
TLDR
We introduce a novel strategy for learning to extract semantically meaningful features from aerial imagery. Expand
  • 57
  • 19
  • PDF
Consistent Temporal Variations in Many Outdoor Scenes
TLDR
This paper details an empirical study of large image sets taken by static cameras. Expand
  • 172
  • 14
  • PDF
Revisiting IM2GPS in the Deep Learning Era
TLDR
We propose to combine this approach with the original Im2GPS approach in which a query image is matched against a database of geotagged images and the location is inferred from the retrieved set. Expand
  • 44
  • 10
  • PDF
Horizon Lines in the Wild
TLDR
We introduce Horizon Lines in the Wild (HLW), a new dataset for single image horizon line estimation, to address the limitations of existing horizon line detection datasets. Expand
  • 40
  • 10
  • PDF
Detecting Vanishing Points Using Global Image Context in a Non-ManhattanWorld
TLDR
We propose a novel method for detecting horizontal vanishing points and the zenith vanishing point in man-made environments and achieve state-of-the-art performance on each dataset. Expand
  • 53
  • 9
  • PDF
The global network of outdoor webcams: properties and applications
TLDR
We characterize the live imaging capabilities of thousands of outdoor webcams which are freely available as of the summer of 2009 in terms of the spatial distribution of the cameras, their update rate, and characteristics of the scene in view. Expand
  • 90
  • 5
  • PDF
Sky segmentation in the wild: An empirical study
TLDR
This paper presents the results of a large-scale empirical evaluation of the performance of three state-of-the-art approaches on a new dataset, which consists of roughly 100k images captured "in the wild". Expand
  • 20
  • 5
  • PDF
A Unified Model for Near and Remote Sensing
TLDR
We propose a novel convolutional neural network architecture for estimating geospatial functions such as population density, land cover, or land use. Expand
  • 33
  • 4
  • PDF
Adventures in archiving and using three years of webcam images
TLDR
This paper details steps we have taken to make this dataset more easily useful to the research community, including (a) tools for finding stable temporal segments, and stabilizing images when the camera is nearly stable, (b) visualization tools to quickly summarize a years worth of image data from one camera and to give a set of exemplars that highlight anomalies within the scene, and (c) integration with LabelMe. Expand
  • 27
  • 4
  • PDF