Multi-Field De-interlacing using Deformable Convolution Residual Blocks and Self-Attention

TL;DR

This paper introduces a novel deep learning model for multi-field deinterlacing that leverages deformable convolution residual blocks and self-attention, achieving state-of-the-art results in both numerical and perceptual metrics.

Contribution

The paper presents a new multi-field deinterlacing network adapting super-resolution techniques with deformable convolutions and self-attention, specifically designed for the deinterlacing task.

Findings

Achieves state-of-the-art deinterlacing performance

Ranks first in the Full FrameRate LeaderBoard

Demonstrates superior numerical and perceptual results

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