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

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

21 Sep 2022arXiv:2209.10192archive 2025-07-28

Ronglei Ji, A. Murat Tekalp

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

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Super-ResolutionVideo DeinterlacingVideo Restoration

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Deinterlacing MSU Deinterlacer Benchmark DfRes (SA) FPS on CPU 0.1 #3 of 31 Archive leaderboard report
Video Deinterlacing MSU Deinterlacer Benchmark DfRes (SA) PSNR 43.486 #3 of 31 Archive leaderboard report
Video Deinterlacing MSU Deinterlacer Benchmark DfRes (SA) SSIM 0.972 #3 of 31 Archive leaderboard report
Video Deinterlacing MSU Deinterlacer Benchmark DfRes (SA) Subjective 0.925 #3 of 31 Archive leaderboard report
Video Deinterlacing MSU Deinterlacer Benchmark DfRes (SA) VMAF 95.96 #3 of 31 Archive leaderboard report
Video Deinterlacing MSU Deinterlacer Benchmark DfRes FPS on CPU 0.4 #4 of 31 Archive leaderboard report
Video Deinterlacing MSU Deinterlacer Benchmark DfRes PSNR 40.590 #4 of 31 Archive leaderboard report
Video Deinterlacing MSU Deinterlacer Benchmark DfRes SSIM 0.971 #4 of 31 Archive leaderboard report
Video Deinterlacing MSU Deinterlacer Benchmark DfRes Subjective 0.912 #4 of 31 Archive leaderboard report
Video Deinterlacing MSU Deinterlacer Benchmark DfRes VMAF 95.20 #4 of 31 Archive leaderboard report
Video Deinterlacing MSU Deinterlacer Benchmark DfRes (122000 G2e 3) PSNR 43.200 #6 of 31 Archive leaderboard report
Video Deinterlacing MSU Deinterlacer Benchmark DfRes (122000 G2e 3) SSIM 0.972 #6 of 31 Archive leaderboard report
Video Deinterlacing MSU Deinterlacer Benchmark DfRes (122000 G2e 3) Subjective 0.862 #6 of 31 Archive leaderboard report
Video Deinterlacing MSU Deinterlacer Benchmark DfRes (122000 G2e 3) VMAF 95.68 #6 of 31 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

ConvolutionDeformable Convolution

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections