Related papers: Geospecific View Generation -- Geometry-Context Aw…
There has recently been great interest in neural rendering methods. Some approaches use 3D geometry reconstructed with Multi-View Stereo (MVS) but cannot recover from the errors of this process, while others directly learn a volumetric…
Contextual information can have a substantial impact on the performance of visual tasks such as semantic segmentation, object detection, and geometric estimation. Data stored in Geographic Information Systems (GIS) offers a rich source of…
Camera-controlled video generation has achieved remarkable progress in recent years. However, existing video-to-video re-rendering methods primarily rely on Supervised Fine-Tuning using synthetic datasets. At present, there is an extreme…
This paper presents a learning-based approach to synthesize the view from an arbitrary camera position given a sparse set of images. A key challenge for this novel view synthesis arises from the reconstruction process, when the views from…
We present a novel method for synthesizing both temporally and geometrically consistent street-view panoramic video from a single satellite image and camera trajectory. Existing cross-view synthesis approaches focus on images, while video…
We explore the task of geometric reconstruction of images captured from a mixture of ground and aerial views. Current state-of-the-art learning-based approaches fail to handle the extreme viewpoint variation between aerial-ground image…
Synthesizing novel views from monocular videos of dynamic scenes remains a challenging problem. Scene-specific methods that optimize 4D representations with explicit motion priors often break down in highly dynamic regions where multi-view…
3D Gaussians have recently emerged as an effective scene representation for real-time splatting and accurate novel-view synthesis, motivating several works to adapt multi-view structure prediction networks to regress per-pixel 3D Gaussians…
This paper proposes a fine-grained self-localization method for outdoor robotics that utilizes a flexible number of onboard cameras and readily accessible satellite images. The proposed method addresses limitations in existing cross-view…
Worldwide image geolocalization, which aims to predict the GPS coordinates of any image on Earth, remains challenging due to global visual diversity. Recent generative approaches based on Retrieval-Augmented Generation (RAG) and Large…
Cross-view geo-localization aims at localizing a ground-level query image by matching it to its corresponding geo-referenced aerial view. In real-world scenarios, the task requires accommodating diverse ground images captured by users with…
Recent advances in optimizing Gaussian Splatting for scene geometry have enabled efficient reconstruction of detailed surfaces from images. However, when input views are sparse, such optimization is prone to overfitting, leading to…
Despite recent advancements in image generation, diffusion models still remain largely underexplored in Earth Observation. In this paper we show that state-of-the-art pretrained diffusion models can be conditioned on cartographic data to…
We propose scene-adaptive strategies to efficiently allocate representation capacity for generating immersive experiences of indoor environments from incomplete observations. Indoor scenes with multiple rooms often exhibit irregular layouts…
We present FaceLift, a novel feed-forward approach for generalizable high-quality 360-degree 3D head reconstruction from a single image. Our pipeline first employs a multi-view latent diffusion model to generate consistent side and back…
Gravitational lensing data is frequently collected at low resolution due to instrumental limitations and observing conditions. Machine learning-based super-resolution techniques offer a method to enhance the resolution of these images,…
We propose a novel image editing technique that enables 3D manipulations on single images, such as object rotation and translation. Existing 3D-aware image editing approaches typically rely on synthetic multi-view datasets for training…
Geospatial imaging leverages data from diverse sensing modalities-such as EO, SAR, and LiDAR, ranging from ground-level drones to satellite views. These heterogeneous inputs offer significant opportunities for scene understanding but…
When viewing a 3D Gaussian Splatting (3DGS) model from camera positions significantly outside the training data distribution, substantial visual noise commonly occurs. These artifacts result from the lack of training data in these…
Aerial image analysis at a semantic level is important in many applications with strong potential impact in industry and consumer use, such as automated mapping, urban planning, real estate and environment monitoring, or disaster relief.…