Multi-Field De-interlacing using Deformable Convolution Residual Blocks and Self-Attention
This addresses the deinterlacing problem for video processing applications, representing an incremental improvement by adapting existing methods to a less-explored task.
The paper tackles the problem of video deinterlacing by proposing a novel network that adapts super-resolution approaches, achieving state-of-the-art results in numerical and perceptual performance as ranked first on a benchmark leaderboard.
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