Spatio-Temporal Deformable Convolution for Compressed Video Quality Enhancement

Deng, Jianing; Wang, Li; Pu, Shiliang; Zhuo, Cheng

doi:10.1609/aaai.v34i07.6697

Cited by 121 publications

(121 citation statements)

References 30 publications

Supporting

Mentioning

108

Contrasting

Order By: Relevance

“…We compare our one-stage FM-VSR to several two-stage methods composed of a SOTA VQE and a VSR networks : MFQE2.0 [8] + TDAN [16], STDF [9] + TDAN, MFQE2.0 + EDVR [18] and STDF + TDAN. Besides, bicubic is also considered as a way for VSR to be compared.…”

Section: ) Comparison To the Two-stage Methodsmentioning

confidence: 99%

See 1 more Smart Citation

FM-VSR: Feature Multiplexing Video Super-Resolution for Compressed Video

Pei

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Due to the limitation of shooting conditions in the real world, there exist many insufficientresolution videos. To be transmitted under limited bandwidth conditions, low-resolution videos often have to be compressed further, which introduces more compression artifacts and results in severer damage to the video quality. Accordingly, video super-resolution in practical applications must repair compressed damage and down-sampling damage simultaneously, which can be intuitively solved by two subtasks, including compressed video quality enhancement (VQE) and video super-resolution (VSR). Therefore, we proposed a novel model, the Feature Multiplexing Video Super-Resolution for Compressed Video (FM-VSR) to effectively handle such multi-tasks. Firstly, we use a complicated Deformable Regression Pyramid (DRP) module to align the reference frame and each supporting frame. Then feature multiplexing structure is utilized in VSR to make better use of the VQE information. Finally, a skip-attention structure is introduced in the reconstruction module to predict the high-quality video frame. Many experiments on benchmark datasets show that our method can achieve better performance both in quantitative and qualitative than the state-of-the-art (SOTA) two-stage approaches. Super-resolution, video compression, deep learning. INDEX TERMS

show abstract

Section: ) Comparison To the Two-stage Methodsmentioning

confidence: 99%

“…Content may change prior to final publication. [9], which has become the latest technology for video quality enhancement.…”

Section: Introductionmentioning

confidence: 99%

FM-VSR: Feature Multiplexing Video Super-Resolution for Compressed Video

Pei

et al. 2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…We compare the proposed DCNGAN with state-of-the-art video quality enhancement networks in [4] (MFQE 2.0), [5] (STDF), [9] (MW-GAN) 1 and [10] (VPE-GAN). LPIPS [17] and DISTS [18] are employed to quantitatively evaluate the perceptual quality of enhanced videos.…”

Section: Quantitative and Qualitative Comparisonmentioning

confidence: 99%

“…Previous works focus on enhancing the objective quality of compressed videos [3] [4] [5]. Yang et al [3] proposed a compressed video quality enhancement algorithm which aggregated information from neighboring high quality frames, named MFQE.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

DCNGAN: A Deformable Convolutional-Based GAN with QP Adaptation for Perceptual Quality Enhancement of Compressed Video

Zhang¹,

Herranz²,

Mrak³

et al. 2022

Preprint

View full text Add to dashboard Cite

In this paper, we propose a deformable convolution-based generative adversarial network (DCNGAN) for perceptual quality enhancement of compressed videos. DCNGAN is also adaptive to the quantization parameters (QPs). Compared with optical flows, deformable convolutions are more effective and efficient to align frames. Deformable convolutions can operate on multiple frames, thus leveraging more temporal information, which is beneficial for enhancing the perceptual quality of compressed videos. Instead of aligning frames in a pairwise manner, the deformable convolution can process multiple frames simultaneously, which leads to lower computational complexity. Experimental results demonstrate that the proposed DCNGAN outperforms other state-of-theart compressed video quality enhancement algorithms.

show abstract

Graph‐based mutually exciting point processes for modelling event times in docked bike‐sharing systems

Sanna Passino,

Che,

Cardoso Correia Perello

2024

Stat

View full text Add to dashboard Cite

This paper introduces graph‐based mutually exciting processes (GB‐MEP) to model event times in network point processes, focusing on an application to docked bike‐sharing systems. GB‐MEP incorporates known relationships between nodes in a graph within the intensity function of a node‐based multivariate Hawkes process. This approach reduces the number of parameters to a quantity proportional to the number of nodes in the network, resulting in significant advantages for computational scalability when compared with traditional methods. The model is applied on event data observed on the Santander Cycles network in central London, demonstrating that exploiting network‐wide information related to geographical location of the stations is beneficial to improve the performance of node‐based models for applications in bike‐sharing systems. The proposed GB‐MEP framework is more generally applicable to any network point process where a distance function between nodes is available, demonstrating wider applicability.

show abstract

Spatio-Temporal Deformable Convolution for Compressed Video Quality Enhancement

Cited by 121 publications

References 30 publications

FM-VSR: Feature Multiplexing Video Super-Resolution for Compressed Video

FM-VSR: Feature Multiplexing Video Super-Resolution for Compressed Video

DCNGAN: A Deformable Convolutional-Based GAN with QP Adaptation for Perceptual Quality Enhancement of Compressed Video

Graph‐based mutually exciting point processes for modelling event times in docked bike‐sharing systems

Contact Info

Product

Resources

About