Modernizing Old Photos Using Multiple References via Photorealistic Style Transfer
This addresses the challenge of restoring and updating historical photographs for applications in digital archiving and personal photo enhancement, representing an incremental improvement in style transfer methods.
The paper tackles the problem of modernizing old photos by using multiple reference images for photorealistic style transfer and enhancement, achieving superior performance over baselines on a new benchmark dataset without training on real old photos.
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.