Retrieval-guided Cross-view Image Synthesis

Abstract

Information retrieval techniques have demonstrated exceptional capabilities in identifying semantic similarities across diverse domains through robust feature representations. However, their potential in guiding synthesis tasks, particularly cross-view image synthesis, remains underexplored. Cross-view image synthesis presents significant challenges in establishing reliable correspondences between drastically different viewpoints. To address this, we propose a novel retrieval-guided framework that reimagines how retrieval techniques can facilitate effective cross-view image synthesis. Unlike existing methods that rely on auxiliary information, such as semantic segmentation maps or preprocessing modules, our retrieval-guided framework captures semantic similarities across different viewpoints, trained through contrastive learning to create a smooth embedding space. Furthermore, a novel fusion mechanism leverages these embeddings to guide image synthesis while learning and encoding both

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyyang2024retrieval

Related papers

• Cross-view Localization And Synthesis -- Datasets, Challenges And Opportunities (2025)2.51
• Cross-view Image Retrieval -- Ground To Aerial Image Retrieval Through Deep Learning (2020)5.24
• Cross-modal Fusion Distillation For Fine-grained Sketch-based Image Retrieval (2022)2.68
• Coming Down To Earth: Satellite-to-street View Synthesis For Geo-localization (2021)16.28
• Fusionbert: Multi-view Image-3d Retrieval Via Cross-attention Visual Fusion And Normal-aware 3D Encoder (2026)0.00
• Bridging The Domain Gap For Ground-to-aerial Image Matching (2019)16.14
• Freeview Sketching: View-aware Fine-grained Sketch-based Image Retrieval (2024)6.34
• Crossatnet - A Novel Cross-attention Based Framework For Sketch-based Image Retrieval (2021)11.29