paper-with-me

홈 › Papers

Image Retrieval for Structure-from-Motion via Graph Convolutional Network

2020-09-17 · Shen Yan, Yang Pen, Shiming Lai, Yu Liu, Maojun Zhang

Conventional image retrieval techniques for Structure-from-Motion (SfM) suffer from the limit of effectively recognizing repetitive patterns and cannot guarantee to create just enough match pairs with high precision and high recall. In this paper, we present a novel retrieval method based on Graph Convolutional Network (GCN) to generate accurate pairwise matches without costly redundancy. We formulate image retrieval task as a node binary classification problem in graph data: a node is marked as positive if it shares the scene overlaps with the query image. The key idea is that we find that the local context in feature space around a query image contains rich information about the matchable relation between this image and its neighbors. By constructing a subgraph surrounding the query image as input data, we adopt a learnable GCN to exploit whether nodes in the subgraph have overlapping regions with the query photograph. Experiments demonstrate that our method performs remarkably well on the challenging dataset of highly ambiguous and duplicated scenes. Besides, compared with state-of-the-art matchable retrieval methods, the proposed approach significantly reduces useless attempted matches without sacrificing the accuracy and completeness of reconstruction.

📄 PDF Abstract BibTeX arXiv:2009.08049

Code (0)

등록된 구현이 없습니다.

Tasks

Binary ClassificationImage RetrievalRetrieval

Methods 이 논문이 사용한 방법론

GCN A Graph Convolutional Network, or GCN, is an approach for semi-supervised learning on graph-structured data. It is based on an efficient variant of [convolutional neural…

Similar Papers 제목 키워드 기반

Learning Quantised Structure-Preserving Motion Representations for Dance Fingerprinting

2026-04-01 · Arina Kharlamova, Bowei He, Chen Ma, Xue Liu arxiv

We present DANCEMATCH, an end-to-end framework for motion-based dance retrieval, the task of identifying semantically similar choreographies directly from raw video, defined as DANCE FINGERPRINTING. While existing motion…

CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples

2016-04-08 · Filip Radenović, Giorgos Tolias, Ondřej Chum

Convolutional Neural Networks (CNNs) achieve state-of-the-art performance in many computer vision tasks. However, this achievement is preceded by extreme manual annotation in order to perform either training from scratch…

Image RetrievalRetrieval

SupScene: Scene-Structured Overlap Supervision for Image Retrieval in Unconstrained SfM

2026-01-17 · Xulei Shi, Maoyu Wang, Yuning Peng, Guanbo Wang 외 arxiv

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 geometri…

Image RetrievalImage Matching

Scene Graph Embeddings Using Relative Similarity Supervision

2021-04-06 · Paridhi Maheshwari, Ritwick Chaudhry, Vishwa Vinay

Scene graphs are a powerful structured representation of the underlying content of images, and embeddings derived from them have been shown to be useful in multiple downstream tasks. In this work, we employ a graph convo…

Contrastive LearningImage RetrievalRetrieval

Fine-tuning CNN Image Retrieval with No Human Annotation

2017-11-03 · Filip Radenović, Giorgos Tolias, Ondřej Chum

Image descriptors based on activations of Convolutional Neural Networks (CNNs) have become dominant in image retrieval due to their discriminative power, compactness of representation, and search efficiency. Training of …

Image RetrievalRetrieval