Purely Geometric Scene Association And Retrieval - A Case For Macro Scale 3D Geometry

Abstract

We address the problems of measuring geometric similarity between 3D scenes, represented through point clouds or range data frames, and associating them. Our approach leverages macro-scale 3D structural geometry - the relative configuration of arbitrary surfaces and relationships among structures that are potentially far apart. We express such discriminative information in a viewpoint-invariant feature space. These are subsequently encoded in a frame-level signature that can be utilized to measure geometric similarity. Such a characterization is robust to noise, incomplete and partially overlapping data besides viewpoint changes. We show how it can be employed to select a diverse set of data frames which have structurally similar content, and how to validate whether views with similar geometric content are from the same scene. The problem is formulated as one of general purpose retrieval from an unannotated, spatio-temporally unordered database. Empirical analysis indicates that the pr

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keysawhney2018purely

Related papers

• Generating Holistic 3D Scene Abstractions For Text-based Image Retrieval (2016)9.03
• 3D Shape Knowledge Graph For Cross-domain 3D Shape Retrieval (2022)5.24
• Method For The Generation Of Depth Images For View-based Shape Retrieval Of 3D CAD Model From Partial Point Cloud (2020)9.41
• Aggregation Of Binary Feature Descriptors For Compact Scene Model Representation In Large Scale Structure-from-motion Applications (2018)0.00
• Weakly-supervised End-to-end CAD Retrieval To Scan Objects (2022)0.00
• COM3D: Leveraging Cross-view Correspondence And Cross-modal Mining For 3D Retrieval (2024)3.58
• Predicting Visual Overlap Of Images Through Interpretable Non-metric Box Embeddings (2020)8.82
• Supscene: Scene-structured Overlap Supervision For Image Retrieval In Unconstrained Sfm (2026)2.20