• Publications
  • Influence
Predicting Ground-Level Scene Layout from Aerial Imagery
TLDR
A novel strategy for learning to extract semantically meaningful features from aerial imagery is introduced to predict (noisy) semantic features automatically extracted from co-located ground imagery and it is demonstrated that by finetuning this model, it can achieve more accurate semantic segmentation than two baseline initialization strategies. Expand
Wide-Area Image Geolocalization with Aerial Reference Imagery
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 toExpand
Detecting Vanishing Points Using Global Image Context in a Non-ManhattanWorld
TLDR
A novel method for detecting horizontal vanishing points and the zenith vanishing point in man-made environments that uses the use of global image context, extracted with a deep convolutional network, to constrain the set of candidates under consideration. Expand
Horizon Lines in the Wild
TLDR
This work introduces a large, realistic evaluation dataset, Horizon Lines in the Wild (HLW), containing natural images with labeled horizon lines, and investigates the application of convolutional neural networks for directly estimating the horizon line. Expand
Sky segmentation in the wild: An empirical study
TLDR
A deep learning based variant of an ensemble solution that outperforms the methods tested, in some cases achieving above 50% relative reduction in misclassified pixels is proposed. Expand
A Unified Model for Near and Remote Sensing
TLDR
A novel convolutional neural network architecture for estimating geospatial functions such as population density, land cover, or land use is proposed, which uses kernel regression and density estimation to convert features extracted from the ground-level images into a dense feature map. Expand
DEEPFOCAL: A method for direct focal length estimation
TLDR
This work explores the application of a deep convolutional neural network, trained on natural images obtained from Internet photo collections, to directly estimate the focal length using only raw pixel intensities as input features. Expand
Understanding and Mapping Natural Beauty
TLDR
It is demonstrated that quantitative measures of scenicness can benefit semantic image understanding, content-aware image processing, and a novel application of cross-view mapping, where the sparsity of ground-level images can be addressed by incorporating unlabeled overhead images in the training and prediction steps. Expand
On the location dependence of convolutional neural network features
TLDR
This work compares features extracted from various layers of convolutional neural networks and analyzes their discriminative ability with regards to location to investigate the usefulness of deep learned features for high-level computer vision problems. Expand
Analyzing human appearance as a cue for dating images
TLDR
The results show that human appearance is strongly related to time and that semantic information can be a useful cue. Expand
...
1
2
3
4
5
...