Abstract
Video denoising is a fundamental problem in numerous computer vision applications. State-of-the-art attention-based denoising methods typically yield good results, but require vast amounts of GPU memory and usually suffer from very long computation times. Especially in the field of restoring digitized high-resolution historic films, these techniques are not applicable in practice. To overcome these issues, we introduce a lightweight video denoising network that combines efficient axial-coronal-sagittal (ACS) convolutions with a novel shifted window attention formulation (ASwin), which is based on the memory-efficient aggregation of self- and cross-attention across video frames. We numerically validate the performance and efficiency of our approach on synthetic Gaussian noise. Moreover, we train our network as a general-purpose blind denoising model for real-world videos, using a realistic noise synthesis pipeline to generate clean-noisy video pairs. A user study and non-reference quality assessment prove that our method outperforms the state-of-the-art on real-world historic videos in terms of denoising performance and temporal consistency.
Original language | English |
---|---|
Title of host publication | Proceedings - 2023 IEEE Winter Conference on Applications of Computer Vision, WACV 2023 |
Publisher | Institute of Electrical and Electronics Engineers |
Pages | 351-360 |
Number of pages | 10 |
ISBN (Electronic) | 9781665493468 |
DOIs | |
Publication status | Published - 2023 |
Event | 23rd IEEE/CVF Winter Conference on Applications of Computer Vision: WACV 2023 - Waikoloa, United States Duration: 3 Jan 2023 → 7 Jan 2023 https://wacv2023.thecvf.com/home |
Conference
Conference | 23rd IEEE/CVF Winter Conference on Applications of Computer Vision |
---|---|
Abbreviated title | WACV 2023 |
Country/Territory | United States |
City | Waikoloa |
Period | 3/01/23 → 7/01/23 |
Internet address |
Keywords
- Algorithms: Computational photography
- and algorithms (including transfer, low-shot, semi-, self-, and un-supervised learning)
- formulations
- image and video synthesis
- Low-level and physics-based vision
- Machine learning architectures
ASJC Scopus subject areas
- Artificial Intelligence
- Computer Science Applications
- Computer Vision and Pattern Recognition