Publication:
Multi-field de-interlacing using deformable convolution residual blocks and self-attention

Thumbnail Image

School / College / Institute

Organizational Unit

Program

KU Authors

Co-Authors

Publication Date

Language

Embargo Status

Journal Title

Journal ISSN

Volume Title

Alternative 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.

Source

Publisher

The Institute of Electrical and Electronics Engineers Signal Processing Society

Subject

Computer Science, Artificial intelligence, Electrical electronics engineering

Citation

Has Part

Source

Proceedings - International Conference on Image Processing, ICIP

Book Series Title

Edition

DOI

10.1109/ICIP46576.2022.9897353

item.page.datauri

Link

Rights

Copyrights Note

Endorsement

Review

Supplemented By

Referenced By

3

Views

4

Downloads

View PlumX Details