Early interlaced videos usually contain multiple and interlacing and complex compression artifacts, which significantly reduce the visual quality. Although the high-definition reconstruction technology for early videos has made great progress in recent years, related research on deinterlacing is still lacking. Traditional methods mainly focus on simple interlacing mechanism, and cannot deal with the complex artifacts in real-world early videos. Recent interlaced video reconstruction deep deinterlacing models only focus on single frame, while neglecting important temporal information. Therefore, this paper proposes a multiframe deinterlacing network joint enhancement network for early interlaced videos that consists of three modules, i.e., spatial vertical interpolation module, temporal alignment and fusion module, and final refinement module. The proposed method can effectively remove the complex artifacts in early videos by using temporal redundancy of multi-fields. Experimental results demonstrate that the proposed method can recover high quality results for both synthetic dataset and real-world early interlaced videos.
Interlaced dynamic XCT reconstruction with spatio-temporal implicit neural representations
Nuclear Science and Engineering, Massachusetts Institute of Technology（麻省理工学院核科学与工程系）；École Polytechnique de Bruxelles, Université Libre de Bruxelles（布鲁塞尔联邦理工学院）；Electrical Engineering and Computer Science, Massachusetts Institute of Technology（麻省理工学院电气工程与计算机科学系）
Learning-Based Video Coding with Joint Deep Compression and Enhancement
Fuzhou University（福州大学）；Peking University（北京大学）
基于学习的端到端视频压缩技术是将视频信号压缩为叠加的视觉特征的另一种方法，引起了人们的广泛关注。本文提出了一种高效的端到端深度视频编解码器与联合优化的压缩和增强模块（JCEVC）。首先，我们提出了一个双路径生成对抗网络（DPEG）来重建压缩后的视频细节。一个$α$路径有利于结构信息重建与大的感受野和多帧参考，而一个$β$路径有利于局部纹理的重建。这两条路径在生成对抗过程中融合并共同训练。其次，我们在运动补偿和质量增强模块中重用DPEG网络，并将其与其他必要模块结合起来，以制定我们的JCEVC框架。第三，我们采用深度视频压缩和增强的联合训练，进一步提高了压缩的率失真（RD）性能。与x265 LDP very fast模式相比，我们的JCEVC在相同的PSNR/MS-SSIM下，平均每像素比特数（bpp）降低了39.39\%/54.92\%，这比最先进的深度视频编解码器有相当大的优势。
LoLiSRFlow: Joint Single Image Low-light Enhancement and Super-resolution via Cross-scale Transformer-based Conditional Flow
School of Mathematical Science, Dalian University of Technology（大连理工大学数学科学学院）；School of Software Technology, Dalian University of Technology（大连理工大学软件学院）；National University of Defense Technology（国防科技大学）
Blind Quality Enhancement for G-PCC Compressed Dynamic Point Clouds
School of Control Science and Engineering, Shandong University（山东大学控制科学与工程学院）；Key Laboratory of Machine Intelligence and System Control, Ministry of Education（教育部机器智能与系统控制重点实验室）；School of Engineering, Infrastructure and Sustainability, De Montfort University（德蒙福特大学工程、基础设施与可持续学院）；Department of Computing and Decision Science, Lingnan University（岭南大学计算与决策科学系）
