VALSE 论文速览 第102期：基于对偶对抗自适应的跨设备真实图像超分辨率 ...

论文题目：Dual Adversarial Adaptation for Cross-Device Real-World Image Super-Resolution

作者列表：许晓倩†(中山大学)、魏朋旭*(中山大学)、陈伟凯(腾讯美国)、刘阳(中山大学)、毛明志(中山大学)、林倞(中山大学)、李冠彬(中山大学)

B站观看网址：

https://www.bilibili.com/video/BV1584y1v7T8/

论文摘要：

Due to the sophisticated imaging process, an identical scene captured by different cameras could exhibit distinct imaging patterns, introducing distinct proficiency among the super-resolution (SR)models trained on images from different devices. In this paper, we investigate a novel and practical task coded cross-device SR, which strives to adapt a real-world SR model trained on the paired images captured by one camera to low-resolution (LR)images captured by arbitrary target devices. The proposed task is highly challenging due to the absence of paired data from various imaging devices. To address this issue, we propose an unsupervised domain adaptation mechanism for real-world SR, named Dual ADversarial Adaptation (DADA), which only requires LR images in the target domain with available real paired data from a source camera. DADA employs the Domain-Invariant Attention (DIA)module to establish the basis of target model training even without HR supervision. Furthermore, the dual framework of DADA facilitates an Inter-domain Adversarial Adaptation (InterAA)in one branch for two LR input images from two domains, and an Intra-domain Adversarial Adaptation (IntraAA)in two branches for an LR input image. InterAA and IntraAA together improve the model transferability from the source domain to the target. We empirically conduct experiments under six Real to Real adaptation settings among three different cameras, and achieve superior performance compared with existing state-of-the-art approaches. We also evaluate the proposed DADA to address the adaptation to the video camera, which presents a promising research topic to promote the wide applications of real-world super-resolution.

论文信息：

[1] X. Xu, P. Wei, W. Chen, Y. Liu, M. Mao, L. Lin, and G. Li. Dual Adversarial Adaptation for Cross-Device Real-World Image Super-Resolution. In CVPR, 2022.

论文链接：

[https://openaccess.thecvf.com/content/CVPR2022/papers/Xu_Dual_Adversarial_Adaptation_for_Cross-Device_Real-World_Image_Super-Resolution_CVPR_2022_paper.pdf]

代码链接：

[https://github.com/lonelyhope/DADA]

视频讲者简介：

魏朋旭，中山大学计算机学院副研究员。主要研究方向为计算机视觉，尤其是真实图像超分辨率数据基准及方法的研究，以及视觉模型的鲁棒性和可迁移。在TPAMI、CVPR等顶级期刊和会议发表多篇论文。

特别鸣谢本次论文速览主要组织者：

月度轮值AC：李冠彬 (中山大学)、李镇 (香港中文大学 (深圳))

季度责任AC：张姗姗 (南京理工大学)