Publication: Multi-field de-interlacing using deformable convolution residual blocks and self-attention
Program
KU-Authors
KU Authors
Co-Authors
Advisor
Publication Date
2022
Language
English
Type
Conference proceeding
Journal Title
Journal ISSN
Volume Title
Abstract
Although deep learning has made significant impact on image/video restoration and super-resolution, learned deinterlacing has so far received less attention in academia or industry. This is despite deinterlacing is well-suited for supervised learning from synthetic data since the degradation model is known and fixed. In this paper, we propose a novel multi-field full frame-rate deinterlacing network, which adapts the state-of-the-art superresolution approaches to the deinterlacing task. Our model aligns features from adjacent fields to a reference field (to be deinterlaced) using both deformable convolution residual blocks and self attention. Our extensive experimental results demonstrate that the proposed method provides state-of-the-art deinterlacing results in terms of both numerical and perceptual performance. At the time of writing, our model ranks first in the Full FrameRate LeaderBoard at https://videoprocessing.ai/benchmarks/deinterlacer.html.
Description
Source:
Proceedings - International Conference on Image Processing, ICIP
Publisher:
The Institute of Electrical and Electronics Engineers Signal Processing Society
Keywords:
Subject
Computer Science, Artificial intelligence, Electrical electronics engineering