| Paper ID | IVMSP-20.3 |
| Paper Title |
LEARNING MODEL-BLIND TEMPORAL DENOISERS WITHOUT GROUND TRUTHS |
| Authors |
Yanghao Li, Bichuan Guo, Jiangtao Wen, Tsinghua University, China; Zhen Xia, Shan Liu, Tencent Media Lab, China; Yuxing Han, Research Institute of Tsinghua University in Shenzhen, China |
| Session | IVMSP-20: Denoising and Deblurring |
| Location | Gather.Town |
| Session Time: | Thursday, 10 June, 13:00 - 13:45 |
| Presentation Time: | Thursday, 10 June, 13:00 - 13:45 |
| Presentation |
Poster
|
| Topic |
Image, Video, and Multidimensional Signal Processing: [IVTEC] Image & Video Processing Techniques |
| IEEE Xplore Open Preview |
Click here to view in IEEE Xplore |
| Virtual Presentation |
Click here to watch in the Virtual Conference |
| Abstract |
Denoisers trained with synthetic noises often fail to cope with the diversity of real noises, giving way to methods that can adapt to unknown noise without noise modeling or ground truth. Previous image-based method leads to noise overfitting if directly applied to temporal denoising, and has inadequate temporal information management especially in terms of occlusion and lighting variation. In this paper, we propose a general framework for temporal denoising that successfully addresses these challenges. A novel twin sampler assembles training data by decoupling inputs from targets without altering semantics, which not only solves the noise overfitting problem, but also generates better occlusion masks by check-ing optical flow consistency. Lighting variation is quantified based on the local similarity of aligned frames. Our method consistently outperforms the prior art by 0.6-3.2dB PSNR on multiple noises, datasets and network architectures. State-of-the-art results on reducing model-blind video noises are achieved. |
