Super-Resolution for Overhead Imagery Using DenseNets and Adversarial Learning
Recent advances in Generative Adversarial Learning allow for new modalities of image super-resolution by learning low to high resolution mappings. In this paper we present our work using Generative Adversarial Networks (GANs) with applications to overhead and satellite imagery. We have experimented with several state-of-the-art architectures. We propose a GAN-based architecture using densely connected convolutional neural networks (DenseNets) to be able to super-resolve overhead imagery with a factor of up to 8x. We have also investigated resolution limits of these networks. We report results on several publicly available datasets, including SpaceNet data and IARPA Multi-View Stereo Challenge, and compare performance with other state-of-the-art architectures.
Code (0)
등록된 구현이 없습니다.
Tasks
Image Super-ResolutionSuper-ResolutionSimilar Papers 제목 키워드 기반
Investigation of Densely Connected Convolutional Networks with Domain Adversarial Learning for Noise Robust Speech Recognition
We investigate densely connected convolutional networks (DenseNets) and their extension with domain adversarial training for noise robust speech recognition. DenseNets are very deep, compact convolutional neural networks…
Robust Speech Recognitionspeech-recognitionSpeech RecognitionHandling Image and Label Resolution Mismatch in Remote Sensing
Though semantic segmentation has been heavily explored in vision literature, unique challenges remain in the remote sensing domain. One such challenge is how to handle resolution mismatch between overhead imagery and gro…
Semantic SegmentationUnsupervised Super-Resolution of Satellite Imagery for High Fidelity Material Label Transfer
Urban material recognition in remote sensing imagery is a highly relevant, yet extremely challenging problem due to the difficulty of obtaining human annotations, especially on low resolution satellite images. To this en…
Domain AdaptationMaterial RecognitionSuper-ResolutionUnsupervised Domain AdaptationUsing Conditional Generative Adversarial Networks to Generate Ground-Level Views From Overhead Imagery
This paper develops a deep-learning framework to synthesize a ground-level view of a location given an overhead image. We propose a novel conditional generative adversarial network (cGAN) in which the trained generator g…
DecoderGeneral ClassificationGenerative Adversarial NetworkLand Cover ClassificationSemantic Segmentation of Medium-Resolution Satellite Imagery using Conditional Generative Adversarial Networks
Semantic segmentation of satellite imagery is a common approach to identify patterns and detect changes around the planet. Most of the state-of-the-art semantic segmentation models are trained in a fully supervised way u…
Image-to-Image TranslationLand Cover ClassificationSegmentationSemantic Segmentation+1