Real-time Deep Video Deinterlacing

Zhu, Haichao; Liu, Xueting; Mao, Xiangyu; Wong, Tien‐Tsin

doi:10.48550/arxiv.1708.00187

Cited by 4 publications

(15 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed MFDIN is compared with traditional single field vertical interpolation (SFI) and recent DNN-based deinterlacing methods, i.e., DICNN [4] and DIN [5]. In addition, we also retrained a deeper single-frame model EDSR [3] with 16RBs and a SOTA multi-frame model EDVR [7].…”

Section: Results On the Synthetic Testing Setsmentioning

confidence: 99%

“…It can be seen that simple SFI method can reduce the comb-teeth effect, but it also enlarges various mixed artifacts. DICNN [4] is a lightweight shallow network with few parameters. However, it is only designed for real-time deinterlacing tasks, and thus cannot handle the complex noise in early videos.…”

Section: Results On the Synthetic Testing Setsmentioning

confidence: 99%

“…But they cannot solve deinterlacing task directly, since interlacing is caused by specific manmade mechanisms. DICNN [4] first introduced shallow convolutional networks to the real-time video de-interlacing task. However, this model still ignores the mixture of various kinds of unnatural effects in real-world early interlaced videos.…”

Section: Odd Field Even Field Interlaced Framementioning

confidence: 99%

“…Existing jointly deinterlacing and denoise methods [5], [6] are based on single-frame reconstruction and cannot make full use of the temporal similarity between adjacent frames. However, interlaced frames are highly correlated with adjacent frames in time series, hence the performance of current single-frame de-interlacing networks [4]- [6] still has a lot of room for improvement.…”

Section: Odd Field Even Field Interlaced Framementioning

confidence: 99%

“…In recent years, DNN-based methods [19]- [23] have achieved much better performance than traditional methods in many low-level vision tasks. Zhu et al [4] first introduced a shallow deinterlacing convolutional neural network (DICNN) to video deinterlacing tasks and achieved impressive results. However, the learning ability of shallow networks is limited, and complex artifacts in realworld interlaced videos cannot be handled well in this manner.…”

Section: Odd Field Even Field Interlaced Framementioning

confidence: 99%

See 4 more Smart Citations

Multi-frame Joint Enhancement for Early Interlaced Videos

Zhao

Chen

et al. 2021

Preprint

View full text Add to dashboard Cite

Early interlaced videos usually contain multiple and interlacing and complex compression artifacts, which significantly reduce the visual quality. Although the high-definition reconstruction technology for early videos has made great progress in recent years, related research on deinterlacing is still lacking. Traditional methods mainly focus on simple interlacing mechanism, and cannot deal with the complex artifacts in realworld early videos. Recent interlaced video reconstruction deep deinterlacing models only focus on single frame, while neglecting important temporal information. Therefore, this paper proposes a multiframe deinterlacing network joint enhancement network for early interlaced videos that consists of three modules, i.e., spatial vertical interpolation module, temporal alignment and fusion module, and final refinement module. The proposed method can effectively remove the complex artifacts in early videos by using temporal redundancy of multi-fields. Experimental results demonstrate that the proposed method can recover high quality results for both synthetic dataset and real-world early interlaced videos.

show abstract

Section: Results On the Synthetic Testing Setsmentioning

confidence: 99%

Section: Results On the Synthetic Testing Setsmentioning

confidence: 99%

Section: Odd Field Even Field Interlaced Framementioning

confidence: 99%

Section: Odd Field Even Field Interlaced Framementioning

confidence: 99%

Section: Odd Field Even Field Interlaced Framementioning

confidence: 99%

See 3 more Smart Citations

Multi-frame Joint Enhancement for Early Interlaced Videos

Zhao

Chen

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

Multi-Field De-Interlacing Using Deformable Convolution Residual Blocks and Self-Attention

Tekalp

2022

2022 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

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 stateof-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

show abstract

Rethinking deinterlacing for early interlaced videos

Zhao

Wang²

2020

Preprint

View full text Add to dashboard Cite

With the rapid development of image restoration techniques, high-definition reconstruction of early videos has achieved impressive results. However, there are few studies about the interlacing artifacts that often appear in early videos and significantly affect visual perception. Traditional deinterlacing approaches are mainly focused on early interlacing scanning systems and thus cannot handle the complex and complicated artifacts in real-world early interlaced videos. Hence, this paper proposes a specific deinterlacing network (DIN), which is motivated by the traditional deinterlacing strategy. The proposed DIN consists of two stages, i.e., a cooperative vertical interpolation stage for split fields, and a merging stage that is applied to perceive movements and remove ghost artifacts. Experimental results demonstrate that the proposed method can effectively remove complex artifacts in early interlaced videos.

show abstract

Real-time Deep Video Deinterlacing

Cited by 4 publications

References 13 publications

Multi-frame Joint Enhancement for Early Interlaced Videos

Multi-frame Joint Enhancement for Early Interlaced Videos

Multi-Field De-Interlacing Using Deformable Convolution Residual Blocks and Self-Attention

Rethinking deinterlacing for early interlaced videos

Contact Info

Product

Resources

About