Modernizing Old Photos Using Multiple References via Photorealistic Style Transfer

TL;DR

This paper introduces a novel multi-reference framework for old photo modernization that combines photorealistic style transfer and enhancement, trained on synthetic data, and evaluated on a new benchmark dataset, outperforming existing methods.

Contribution

The paper proposes MROPM-Net and a synthetic data scheme for effective multi-reference old photo modernization, including a new benchmark dataset and style selection for improved results.

Findings

Outperforms baseline methods in old photo modernization

Effectively utilizes multiple references for style transfer

Achieves high-quality results without using real old photos in training

Abstract

This paper firstly presents old photo modernization using multiple references by performing stylization and enhancement in a unified manner. In order to modernize old photos, we propose a novel multi-reference-based old photo modernization (MROPM) framework consisting of a network MROPM-Net and a novel synthetic data generation scheme. MROPM-Net stylizes old photos using multiple references via photorealistic style transfer (PST) and further enhances the results to produce modern-looking images. Meanwhile, the synthetic data generation scheme trains the network to effectively utilize multiple references to perform modernization. To evaluate the performance, we propose a new old photos benchmark dataset (CHD) consisting of diverse natural indoor and outdoor scenes. Extensive experiments show that the proposed method outperforms other baselines in performing modernization on real old photos, even though no old photos were used during training. Moreover, our method can appropriately select styles from multiple references for each semantic region in the old photo to further improve the modernization performance.