3DSRnet: Video Super-resolution using 3D Convolutional Neural Networks

Kim, Soo Ye; Lim, Jeongyeon; Na, Taeyoung; Kim, Munchurl

doi:10.48550/arxiv.1812.09079

Cited by 9 publications

(17 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, for the areas contain occlusion and large motion, it is difficult and high-computational-cost to obtain accurate flow. 3D convolution can also be used to achieve temporal aggregation [30]- [32]. For instance, Joe et al [31] used stacked 3D convolution layers for motion compensation to extract temporal information.…”

Section: B Related Multi-frame Video Restorationmentioning

confidence: 99%

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: B Related Multi-frame Video Restorationmentioning

confidence: 99%

Multi-frame Joint Enhancement for Early Interlaced Videos

Zhao

Chen

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The first group of methods process video sequences without any explicit alignment. For example, methods of [19,22] utilize 3D convolutions to directly extract features from multiple frames. Although this approach is simple, the computational cost is typically high.…”

Section: Video Super-resolutionmentioning

confidence: 99%

“…Early methods [24,26] for VSR used various delicate image models, which are solved via optimization techniques. Recent deep-neural-network-based VSR methods [19,22,38,41,37,2,23,26,11,32] further push the limit and set new stateof-the-arts.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

MuCAN: Multi-Correspondence Aggregation Network for Video Super-Resolution

Li¹,

Xin²,

Guo³

et al. 2020

Preprint

View full text Add to dashboard Cite

Video super-resolution (VSR) aims to utilize multiple lowresolution frames to generate a high-resolution prediction for each frame. In this process, inter-and intra-frames are the key sources for exploiting temporal and spatial information. However, there are a couple of limitations for existing VSR methods. First, optical flow is often used to establish temporal correspondence. But flow estimation itself is errorprone and affects recovery results. Second, similar patterns existing in natural images are rarely exploited for the VSR task. Motivated by these findings, we propose a temporal multi-correspondence aggregation strategy to leverage similar patches across frames, and a cross-scale nonlocal-correspondence aggregation scheme to explore self-similarity of images across scales. Based on these two new modules, we build an effective multi-correspondence aggregation network (MuCAN) for VSR. Our method achieves state-of-the-art results on multiple benchmark datasets. Extensive experiments justify the effectiveness of our method.

show abstract

“…A number of studies apply deformable convolution to further expand the field of feature extraction [7,8]. Many studies use 3D convolution to directly fuse information from adjacent frames [9,10] and so on [18][19][20][21]. However, these models can not perfectly solve the problems existing in SR, such as the existence of artifacts, large amount of model training, weak model generalization ability, etc.…”

Section: Introductionmentioning

confidence: 99%

A Novel Dual Dense Connection Network for Video Super-resolution

Li¹,

Zhu²

2022

Preprint

View full text Add to dashboard Cite

Video super-resolution (VSR) refers to the reconstruction of high-resolution (HR) video from the corresponding low-resolution (LR) video. Recently, VSR has received increasing attention. In this paper, we propose a novel dual dense connection network that can generate high-quality super-resolution (SR) results. The input frames are creatively divided into reference frame, pre-temporal group and post-temporal group, representing information in different time periods. This grouping method provides accurate information of different time periods without causing time information disorder. Meanwhile, we produce a new loss function, which is beneficial to enhance the convergence ability of the model. Experiments show that our model is superior to other advanced models in Vid4 datasets and SPMCS-11 datasets.

show abstract

3DSRnet: Video Super-resolution using 3D Convolutional Neural Networks

Cited by 9 publications

References 0 publications

Multi-frame Joint Enhancement for Early Interlaced Videos

Multi-frame Joint Enhancement for Early Interlaced Videos

MuCAN: Multi-Correspondence Aggregation Network for Video Super-Resolution

A Novel Dual Dense Connection Network for Video Super-resolution

Contact Info

Product

Resources

About