Supscene: Scene-structured Overlap Supervision For Image Retrieval In Unconstrained Sfm

Abstract

Image retrieval is a critical step for reducing the quadratic cost of image matching in unconstrained Structure-from-Motion (SfM). Unlike generic image retrieval, however, the relevant goal of SfM is to identify geometrically matchable image pairs rather than merely semantically similar images. Prevailing methods are largely trained under anchor-centric tuple guidance, which organizes the training around isolated tuples and under-utilizes the dense, graded overlap structure naturally established within a SfM scene. In this work, we present SupScene, a scene-structured training framework that samples connected local subgraphs from SfM overlap graphs and jointly supervises all valid within-subgraph pairwise relations. To explicitly align the trained descriptor with geometric co-visibility, we further introduce an overlap-ordered objective that combines multi-similarity optimization with a continuous relative-overlap ranking term. In addition, the proposed framework is instantiated with a

Stats

• citations0
• S2 citations—
• github stars6
• HF likes0
• heat score2.20
• arxiv keyshi2026supscene

Related papers

• Image Retrieval For Structure-from-motion Via Graph Convolutional Network (2020)9.59
• SCENIR: Visual Semantic Clarity Through Unsupervised Scene Graph Retrieval (2025)0.00
• On-the-fly Sfm: What You Capture Is What You Get (2023)5.24
• Superncn: Neighbourhood Consensus Network For Robust Outdoor Scenes Matching (2019)2.26
• Efficient Match Pair Retrieval For Large-scale UAV Images Via Graph Indexed Global Descriptor (2023)6.77
• Back To The Drawing Board: Rethinking Scene-level Sketch-based Image Retrieval (2025)0.00
• Predicting Visual Overlap Of Images Through Interpretable Non-metric Box Embeddings (2020)8.82
• Scene Graph Embeddings Using Relative Similarity Supervision (2021)7.50