Automatic Synchronization of Multi-User Photo Galleries

TL;DR

This paper introduces a robust method for synchronizing multi-user photo galleries by combining deep visual features, graph construction, and probabilistic modeling, outperforming existing approaches in real-world scenarios.

Contribution

It presents a novel multi-stage approach that improves synchronization accuracy without relying on unrealistic assumptions or heuristics, enhancing applicability to diverse datasets.

Findings

Outperforms existing methods on four public datasets

Effectively estimates temporal offsets across galleries

Demonstrates robustness in real-world scenarios

Abstract

In this paper we address the issue of photo galleries synchronization, where pictures related to the same event are collected by different users. Existing solutions to address the problem are usually based on unrealistic assumptions, like time consistency across photo galleries, and often heavily rely on heuristics, limiting therefore the applicability to real-world scenarios. We propose a solution that achieves better generalization performance for the synchronization task compared to the available literature. The method is characterized by three stages: at first, deep convolutional neural network features are used to assess the visual similarity among the photos; then, pairs of similar photos are detected across different galleries and used to construct a graph; eventually, a probabilistic graphical model is used to estimate the temporal offset of each pair of galleries, by traversing the minimum spanning tree extracted from this graph. The experimental evaluation is conducted on four publicly available datasets covering different types of events, demonstrating the strength of our proposed method. A thorough discussion of the obtained results is provided for a critical assessment of the quality in synchronization.