Georeferenced Cross-View 3D Reconstruction from Ground and Satellite Images
cs.CV
Submitted: 2026-11-05
Updated: 2026-11-05
Terminology
Sources
- UNIGEOCLIP: Unified Geospatial Contrastive Learning
- GeoFlow: Real-Time Fine-Grained Cross-View Geolocalization via Iterative Flow Prediction
- Depth Anything 3: Recovering the Visual Space from Any Views
- Decoupled Weight Decay Regularization
- DINOv2: Learning Robust Visual Features without Supervision
- TIGeR: A Unified Framework for Time, Images and Geo-location Retrieval
- Accenture-NVS1: A Novel View Synthesis Dataset
- EffoVPR: Effective Foundation Model Utilization for Visual Place Recognition
- BevSplat: Resolving Height Ambiguity via Feature-Based Gaussian Primitives for Weakly-Supervised Cross-View Localization
- $\pi^3$: Permutation-Equivariant Visual Geometry Learning
- Sky2Ground: A Benchmark for Site Modeling under Varying Altitude
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs