arXivDaily arXiv每日学术速递 周一至周五更新
​通知:联邦节假日调休:哥伦布日 / 原住民日(Columbus Day / Indigenous Peoples' Day),今日(13日)无更新。
arXiv 2304.04461cs.CVcs.GR

基于多参考图像的逼真风格迁移实现老照片现代化

Modernizing Old Photos Using Multiple References via Photorealistic Style Transfer

Adobe Research(奥多比研究院);Qualcomm(高通公司);ETRI(韩国电子通信研究院);KAIST(韩国科学技术院)

Agus Gunawan, Soo Ye Kim, Hyeonjun Sim, Jae-Ho Lee, Munchurl Kim

AI总结:

本文提出基于多参考的老照片现代化(MROPM)框架,通过逼真风格迁移和增强生成现代图像,并构建CHD基准,实验证明其在真实老照片上优于基线方法。

摘要:

本文首次提出通过以统一方式进行风格化和增强,利用多个参考图像实现老照片现代化。为了实现老照片现代化,我们提出了一个新颖的基于多参考的老照片现代化(MROPM)框架,包含网络MROPM-Net和一种新颖的合成数据生成方案。MROPM-Net通过逼真风格迁移(PST)利用多个参考对老照片进行风格化,并进一步对结果进行增强以生成具有现代外观的图像。同时,合成数据生成方案训练网络以有效利用多个参考来执行现代化。为了评估性能,我们提出了一个新的老照片基准数据集(CHD),包含多样的自然室内和室外场景。大量实验表明,所提出的方法在真实老照片上执行现代化时优于其他基线方法,即使在训练期间没有使用老照片。此外,我们的方法能够从多个参考中为老照片中的每个语义区域适当地选择风格,以进一步提升现代化性能。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑