Sat2Density: Faithful Density Learning from Satellite-Ground Image Pairs
This paper aims to develop an accurate 3D geometry representation of satellite images using satellite-ground image pairs. Our focus is on the challenging problem of 3D-aware ground-views synthesis from a satellite image. We draw inspiration from the density field representation used in volumetric neural rendering and propose a new approach, called Sat2Density. Our method utilizes the properties of ground-view panoramas for the sky and non-sky regions to learn faithful density fields of 3D scenes in a geometric perspective. Unlike other methods that require extra depth information during training, our Sat2Density can automatically learn accurate and faithful 3D geometry via density representation without depth supervision. This advancement significantly improves the ground-view panorama synthesis task. Additionally, our study provides a new geometric perspective to understand the relationship between satellite and ground-view images in 3D space.
Code (1)
Tasks
3D geometryCross-View Image-to-Image TranslationGeneralizable Novel View SynthesisGournd video synthesis from satellite imageImage-to-Image TranslationNeural RenderingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Seeing through Satellite Images at Street Views
This paper studies the task of SatStreet-view synthesis, which aims to render photorealistic street-view panorama images and videos given any satellite image and specified camera positions or trajectories. We formulate t…
High-Cadence Thermospheric Density Estimation enabled by Machine Learning on Solar Imagery
Accurate estimation of thermospheric density is critical for precise modeling of satellite drag forces in low Earth orbit (LEO). Improving this estimation is crucial to tasks such as state estimation, collision avoidance…
Collision AvoidanceDensity EstimationState EstimationA Weakly Supervised Approach for Estimating Spatial Density Functions from High-Resolution Satellite Imagery
We propose a neural network component, the regional aggregation layer, that makes it possible to train a pixel-level density estimator using only coarse-grained density aggregates, which reflect the number of objects in …
K-means Enhanced Density Gradient Analysis for Urban and Transport Metrics Using Multi-Modal Satellite Imagery
This paper presents a novel computational approach for evaluating urban metrics through density gradient analysis using multi-modal satellite imagery, with applications including public transport and other urban systems.…
A multi-task convolutional neural network for mega-city analysis using very high resolution satellite imagery and geospatial data
Mega-city analysis with very high resolution (VHR) satellite images has been drawing increasing interest in the fields of city planning and social investigation. It is known that accurate land-use, urban density, and pop…