Existing video compression (VC) methods primarily aim to reduce the spatial and temporal redundancies between consecutive frames in a video while preserving its quality. In this regard, previous works have achieved remarkable results on videos acquired under specific settings such as instant (known) exposure time and shutter speed which often result in sharp videos. However, when these methods are evaluated on videos captured under different temporal priors, which lead to degradations like motion blur and low frame rate, they fail to maintain the quality of the contents. In this work, we tackle the VC problem in a general scenario where a given video can be blurry due to predefined camera settings or dynamics in the scene. By exploiting the natural trade-off between visual enhancement and data compression, we formulate VC as a min-max optimization problem and propose an effective framework and training strategy to tackle the problem. Extensive experimental results on several benchmark datasets confirm the effectiveness of our method compared to several state-of-the-art VC approaches.
TACTIC: Joint Rate-Distortion-Accuracy Optimisation for Low Bitrate Compression
University of Surrey（萨里大学）
TACTIC：Task-Aware Compression Through Intelligent Coding。我们的有损压缩模型基于特定任务的速率-失真-精度权衡进行学习。通过考虑哪些信息对于后续问题是重要的，系统在低比特率下权衡视觉保真度以获得良好的任务性能。与相同比特率的JPEG相比，我们的方法能够将ImageNet子集分类的准确性提高4.5%。我们还证明了我们的方法对其他问题的适用性，提供了一个3.4%的准确性和4.9%的平均IoU的性能提高任务无关的压缩语义分割。
College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算机与数据科学学院）；Center of China-Singapore International Joint Research Institute（中国-新加坡国际联合研究机构中心）；School of Information Science and Engineering, Shandong Normal University（山东师范大学信息科学与工程学院）；School of Engineering Science, Simon Fraser University（西蒙弗雷泽大学工程科学学院）；School of Computer Science and Technology, University of Chinese Academy of Sciences（中国科学院大学计算机科学与技术学院）；Institute of Information Science, Beijing Jiao Tong University（北京交通大学信息科学学院）
4DGC: Rate-Aware 4D Gaussian Compression for Efficient Streamable Free-Viewpoint Video
Cooperative Medianet Innovation Center, Shanghai Jiao Tong University（上海交通大学合作Medianet创新中心）；School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University（上海交通大学电子信息与电气工程学院）；School of Artificial Intelligence, Shanghai Jiao Tong University（上海交通大学人工智能学院）
Perceptual Image Compression with Cooperative Cross-Modal Side Information
Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Peng Cheng Laboratory（鹏城实验室）；Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies（广东省新型安全智能重点实验室）；Huawei Technologies Company Ltd（华为技术有限公司）；Shenzhen University（深圳大学）
DVC-P: Deep Video Compression with Perceptual Optimizations
Xidian University（西安电子科技大学）；BBC Research & Development（英国广播公司研发中心）；Universitat Autònoma de Barcelona（巴塞罗那自治大学）；Northwestern Polytechnical University（西北工业大学）
