Related papers: Geospecific View Generation -- Geometry-Context Aw…
Recently, 3D Gaussian Splatting has emerged as a prominent research direction owing to its ultrarapid training speed and high-fidelity rendering capabilities. However, the unstructured and irregular nature of Gaussian point clouds poses…
Heterogeneous collections of ground and airborne imagery can readily be used to create high-quality 3D models and novel viewpoint renderings of the observed scene. Standard photogrammetry pipelines generate models in arbitrary coordinate…
Super-resolution is aimed at reconstructing high-resolution images from low-resolution observations. State-of-the-art approaches underpinned with deep learning allow for obtaining outstanding results, generating images of high perceptual…
In this work, we present a novel method for extensive multi-scale generative terrain modeling. At the core of our model is a cascade of superresolution diffusion models that can be combined to produce consistent images across multiple…
Aerial imagery analysis is critical for many research fields. However, obtaining frequent high-quality aerial images is not always accessible due to its high effort and cost requirements. One solution is to use the Ground-to-Aerial (G2A)…
We introduce a deep appearance model for rendering the human face. Inspired by Active Appearance Models, we develop a data-driven rendering pipeline that learns a joint representation of facial geometry and appearance from a multiview…
Cross-view geo-localization aims at establishing location correspondences between different viewpoints. Existing approaches typically learn cross-view correlations through direct feature similarity matching, often overlooking semantic…
The large variation of viewpoint and irrelevant content around the target always hinder accurate image retrieval and its subsequent tasks. In this paper, we investigate an extremely challenging task: given a ground-view image of a landmark,…
Meteorology satellite visible light images is critical for meteorology support and forecast. However, there is no such kind of data during night time. To overcome this, we propose a method based on deep learning to create synthetic…
Data-driven methods such as convolutional neural networks (CNNs) are known to deliver state-of-the-art performance on image recognition tasks when the training data are abundant. However, in some instances, such as change detection in…
Novel view synthesis from images, for example, with 3D Gaussian splatting, has made great progress. Rendering fidelity and speed are now ready even for demanding virtual reality applications. However, the problem of assisting humans in…
Ground-to-aerial image synthesis focuses on generating realistic aerial images from corresponding ground street view images while maintaining consistent content layout, simulating a top-down view. The significant viewpoint difference leads…
Reliable spatial information can be difficult to obtain in planetary remote sensing applications because of errors present in the metadata of images taken with space probes. We have designed a pipeline to address this problem on…
We present a practical and robust deep learning solution for capturing and rendering novel views of complex real world scenes for virtual exploration. Previous approaches either require intractably dense view sampling or provide little to…
We introduce a transformer-based neural network to generate high-resolution (3km) synthetic radar reflectivity fields at scale from geostationary satellite imagery. This work aims to enhance short-term convective-scale forecasts of…
Humans can intuitively compose and arrange scenes in the 3D space for photography. However, can advanced AI image generators plan scenes with similar 3D spatial awareness when creating images from text or image prompts? We present GenSpace,…
Recently, multiple formulations of vision problems as probabilistic inversions of generative models based on computer graphics have been proposed. However, applications to 3D perception from natural images have focused on low-dimensional…
Novel view synthesis from a single image requires inferring occluded regions of objects and scenes whilst simultaneously maintaining semantic and physical consistency with the input. Existing approaches condition neural radiance fields…
Deep networks have recently enjoyed enormous success when applied to recognition and classification problems in computer vision, but their use in graphics problems has been limited. In this work, we present a novel deep architecture that…
Recent advances in deep-learning based methods for image matching have demonstrated their superiority over traditional algorithms, enabling correspondence estimation in challenging scenes with significant differences in viewing angles,…