FPANet: Frequency-based Video Demoireing using Frame-level Post Alignment
This addresses the challenge of video demoireing for improving visual quality in applications like photography or video processing, but it is incremental as it builds on existing spatial methods by adding frequency domain and multi-frame processing.
The paper tackles the problem of removing moiré patterns from videos, which degrade visual quality, by proposing FPANet, a network that learns filters in both frequency and spatial domains and uses multiple frames for temporal consistency, resulting in outperforming state-of-the-art methods on image and video quality metrics.
Moire patterns, created by the interference between overlapping grid patterns in the pixel space, degrade the visual quality of images and videos. Therefore, removing such patterns~(demoireing) is crucial, yet remains a challenge due to their complexities in sizes and distortions. Conventional methods mainly tackle this task by only exploiting the spatial domain of the input images, limiting their capabilities in removing large-scale moire patterns. Therefore, this work proposes FPANet, an image-video demoireing network that learns filters in both frequency and spatial domains, improving the restoration quality by removing various sizes of moire patterns. To further enhance, our model takes multiple consecutive frames, learning to extract frame-invariant content features and outputting better quality temporally consistent images. We demonstrate the effectiveness of our proposed method with a publicly available large-scale dataset, observing that ours outperforms the state-of-the-art approaches in terms of image and video quality metrics and visual experience.