Cross-View Splatter: Feed-Forward View Synthesis with Georeferenced Images

• URL: http://arxiv.org/abs/2605.19656v1
• Date: Tue, 19 May 2026 10:48:42 GMT
• Title: Cross-View Splatter: Feed-Forward View Synthesis with Georeferenced Images
• Abstract summary: We present Cross-View Splatter, a feed-forward method that predicts pixel-aligned Gaussian splats for outdoor scenes captured at ground level AND by satellite.<n>Our method fuses orthorectified satellite views with GPS-tagged ground photos to predict Gaussian splats in a unified 3D coordinate frame.<n>We evaluate our method on a new benchmark for novel-view synthesis with georeferenced imagery allowing comparison to prior state-of-the-art methods.
• Score: 33.73035750424556
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: We present Cross-View Splatter, a feed-forward method that predicts pixel-aligned Gaussian splats for outdoor scenes captured at ground level AND by satellite. Faithful reconstructions require good camera coverage, but ground imagery is time-consuming and hard to capture at scale for large outdoor scenes. Fortunately, satellite imagery can provide a global geometric prior that is easy to access via public APIs. Cross-View Splatter fuses orthorectified satellite views with GPS-tagged ground photos to predict Gaussian splats in a unified 3D coordinate frame. By aligning ground and bird's-eye feature representations, our model improves scene coverage and novel-view synthesis, compared to ground imagery alone. We train on curated georeferenced datasets and paired satellite-terrain data, mined from open mapping services. We evaluate our method on a new benchmark for novel-view synthesis with georeferenced imagery allowing comparison to prior state-of-the-art methods. Our code and data preparation will be available at https://nianticspatial.github.io/cross-view-splatter/.

Related papers

• Pixel-wise Geo-registration of Drone and Satellite Images [46.14662444002411]
  Pixel-level cross-view geo-registration aims to align a query image (e.g., drone) to a geo-referenced satellite map so that every query pixel can be mapped to real-world GPS coordinates.<n>Existing benchmarks largely provide only GPS labels, limiting evaluation to a single coordinate per image.<n>We introduce SkyReg, a dataset and standardized benchmark for pixel-level drone-to-satellite geo-registration.
  arXiv  Detail & Related papers  (2026-08-28T21:50:29Z)
• Satellite-Free Training for Drone-View Geo-Localization [23.183491899036138]
  Drone-view geo-localization aims to determine the location of drones in GPS-denied environments by retrieving the corresponding geotagged satellite tile.<n>In this paper, we propose a satellite-free training framework that converts drone imagery into cross-view compatible representations.
  arXiv  Detail & Related papers  (2026-04-02T03:48:53Z)
• Wrivinder: Towards Spatial Intelligence for Geo-locating Ground Images onto Satellite Imagery [28.971555127858334]
  We introduce Wrivinder, a framework that aggregates multiple ground photographs to align it with overhead satellite imagery.<n>We also release MC-Sat, a curated dataset linking multi-view ground imagery with geo-registered satellite tiles across diverse outdoor environments.<n>In zero-shot experiments, Wrivinder achieves sub-30,m geolocation accuracy across both dense and large-area scenes.
  arXiv  Detail & Related papers  (2026-02-16T17:06:54Z)
• SatDreamer360: Multiview-Consistent Generation of Ground-Level Scenes from Satellite Imagery [18.071734088436077]
  We propose SatDreamer360, a framework that generates geometrically consistent multi-view ground-level panoramas from a single satellite image.<n>Experiments show that SatDreamer360 outperforms existing methods in both satellite-to-ground alignment and multiview consistency.
  arXiv  Detail & Related papers  (2025-05-31T15:15:54Z)
• AerialMegaDepth: Learning Aerial-Ground Reconstruction and View Synthesis [57.249817395828174]
  We propose a scalable framework combining pseudo-synthetic renderings from 3D city-wide meshes with real, ground-level crowd-sourced images.<n>The pseudo-synthetic data simulates a wide range of aerial viewpoints, while the real, crowd-sourced images help improve visual fidelity for ground-level images.<n>Using this hybrid dataset, we fine-tune several state-of-the-art algorithms and achieve significant improvements on real-world, zero-shot aerial-ground tasks.
  arXiv  Detail & Related papers  (2025-04-17T17:57:05Z)
• Game4Loc: A UAV Geo-Localization Benchmark from Game Data [0.0]
  We introduce a more practical UAV geo-localization task including partial matches of cross-view paired data.<n>Experiments demonstrate the effectiveness of our data and training method for UAV geo-localization.
  arXiv  Detail & Related papers  (2024-09-25T13:33:28Z)
• Geospecific View Generation -- Geometry-Context Aware High-resolution Ground View Inference from Satellite Views [5.146618378243241]
  We propose a novel pipeline to generate geospecifc views that maximally respect the weak geometry and texture from multi-view satellite images. Our method directly predicts ground-view images at geolocation by using a comprehensive set of information from the satellite image. We demonstrate our pipeline is the first to generate close-to-real and geospecific ground views merely based on satellite images.
  arXiv  Detail & Related papers  (2024-07-10T21:51:50Z)
• Sat2Scene: 3D Urban Scene Generation from Satellite Images with Diffusion [77.34078223594686]
  We propose a novel architecture for direct 3D scene generation by introducing diffusion models into 3D sparse representations and combining them with neural rendering techniques. Specifically, our approach generates texture colors at the point level for a given geometry using a 3D diffusion model first, which is then transformed into a scene representation in a feed-forward manner. Experiments in two city-scale datasets show that our model demonstrates proficiency in generating photo-realistic street-view image sequences and cross-view urban scenes from satellite imagery.
  arXiv  Detail & Related papers  (2024-01-19T16:15:37Z)
• DiffusionSat: A Generative Foundation Model for Satellite Imagery [63.2807119794691]
  We present DiffusionSat, to date the largest generative foundation model trained on a collection of publicly available large, high-resolution remote sensing datasets. Our method produces realistic samples and can be used to solve multiple generative tasks including temporal generation, superresolution given multi-spectral inputs and in-painting.
  arXiv  Detail & Related papers  (2023-12-06T16:53:17Z)
• Satellite Image Based Cross-view Localization for Autonomous Vehicle [59.72040418584396]
  This paper shows that by using an off-the-shelf high-definition satellite image as a ready-to-use map, we are able to achieve cross-view vehicle localization up to a satisfactory accuracy. Our method is validated on KITTI and Ford Multi-AV Seasonal datasets as ground view and Google Maps as the satellite view.
  arXiv  Detail & Related papers  (2022-07-27T13:16:39Z)
• Accurate 3-DoF Camera Geo-Localization via Ground-to-Satellite Image Matching [102.39635336450262]
  We address the problem of ground-to-satellite image geo-localization by matching a query image captured at the ground level against a large-scale database with geotagged satellite images. Our new method is able to achieve the fine-grained location of a query image, up to pixel size precision of the satellite image.
  arXiv  Detail & Related papers  (2022-03-26T20:10:38Z)
• Embedding Earth: Self-supervised contrastive pre-training for dense land cover classification [61.44538721707377]
  We present Embedding Earth a self-supervised contrastive pre-training method for leveraging the large availability of satellite imagery. We observe significant improvements up to 25% absolute mIoU when pre-trained with our proposed method. We find that learnt features can generalize between disparate regions opening up the possibility of using the proposed pre-training scheme.
  arXiv  Detail & Related papers  (2022-03-11T16:14:14Z)
• Free View Synthesis [100.86844680362196]
  We present a method for novel view synthesis from input images that are freely distributed around a scene. Our method does not rely on a regular arrangement of input views, can synthesize images for free camera movement through the scene, and works for general scenes with unconstrained geometric layouts.
  arXiv  Detail & Related papers  (2020-08-12T18:16:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.