计算机视觉理论与实践 课件 7-图像复原增强.pdf

Lec7 Image Restoration ·AIPKU· 人工智能引论实践课 ·AIPKU · 部分讲义来源与致谢 1. Sung Cheol Park, Min Kyu Park, Moon Gi Kang. Super-resolution image reconstruction: a technical overview. IEEE SPM 2003. 2. Xin Li, Michael T. Orchard. New edge-directed interpolation. IEEE TIP 2001. 3. Xiangjun Zhang, Xiaolin Wu. Image Interpolation by Adaptive 2-D Autoregressive Modeling and Soft-Decision Estimation. IEEE TIP 2008. 4. Chao Dong, Chen Change Loy, Kaiming He, Xiaoou Tang. Learning a Deep Convolutional Network for Image Super-Resolution. ECCV 2014. 5. Jiwon Kim, Jung Kwon Lee, Kyoung Mu Lee. Accurate Image Super-Resolution Using Very Deep Convolutional Networks. CVPR 2016. ·AIPKU · Background • 图像降质 - 视觉信息感知和通信的有效性 - 娱乐多媒体的视觉体验 - 应用领域的特定图像质量要求 - 军事遥感/ 医疗成像等 2 ·AIPKU· Visual Degradation Data Acquisition Degradation before Degradation in Degradation after Data Acquisition Data Acquisition Data Acquisition • Heavy Rain/Snow • Downsample • Scratches • Underwater • Motion Blur • Watermark • Low Light • System Noise • Package Loss • Haze/Sandstorm • Optical Distortion • Compression Loss 3 ·AIPKU · Background • 图像降质的原因 • 采集过程 • 硬件终端性能受限, 如手机摄像头 • 低光照拍摄产生噪声 • 物体运动引起模糊等 • 传输信道 • 信号的丢失 • 大气环境的干扰引入噪声 • 算法设计处理导致 • 图像和视频的压缩编码（量化噪声） 4 ·AIPKU · Background • 通过提升硬件工艺改善图像质量 • 以图像传感器