An Efficient Network Design for Face Video Super-resolution

Feng, Yi; He, Li; Bian, Sige; Tang, Yongming

doi:10.1109/iccvw54120.2021.00176

Cited by 8 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a branch of this field, video super-resolution (VSR) mainly utilizes the spatial information of the current frame and the temporal information between neighboring frames to reconstruct the HR frame. At present, VSR encompasses non-blind VSR [1], blind VSR [2], online VSR [3], and other branches [4], and is widely used in remote sensing [5,6], video surveillance [7,8], face recognition [9,10], and other fields [11,12]. At present, with the development of technology, the resolutions of videos are gradually increasing.…”

Section: Introductionmentioning

confidence: 99%

A Lightweight Recurrent Grouping Attention Network for Video Super-Resolution

Zhu,

2023

Sensors

View full text Add to dashboard Cite

Effective aggregation of temporal information of consecutive frames is the core of achieving video super-resolution. Many scholars have utilized structures such as sliding windows and recurrences to gather the spatio-temporal information of frames. However, although the performances of constructed video super-resolution models are improving, the sizes of the models are also increasing, exacerbating the demand on the equipment. Thus, to reduce the stress on the device, we propose a novel lightweight recurrent grouping attention network. The parameters of this model are only 0.878 M, which is much lower than the current mainstream model for studying video super-resolution. We have designed a forward feature extraction module and a backward feature extraction module to collect temporal information between consecutive frames from two directions. Moreover, a new grouping mechanism is proposed to efficiently collect spatio-temporal information of the reference frame and its neighboring frames. The attention supplementation module is presented to further enhance the information gathering range of the model. The feature reconstruction module aims to aggregate information from different directions to reconstruct high-resolution features. Experiments demonstrate that our model achieves state-of-the-art performance on multiple datasets.

show abstract

Section: Introductionmentioning

confidence: 99%

A Lightweight Recurrent Grouping Attention Network for Video Super-Resolution

Zhu,

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Thus, VSR tends to possess more accurate super-resolution (SR) results than SISR. With the continuous increase of video resolution and the increasing pressure of video storage, VSR has been widely utilized in video surveillance [1], [2], face recognition [3], [4], remote sensing [5]- [8], traffic monitoring [9], [10] and other fields.…”

Section: Introductionmentioning

confidence: 99%

Recurrent Feature Updating Network for Video Super-Resolution

Li,

Zhu

2023

IEEE Access

View full text Add to dashboard Cite

Temporal modeling is the essential to achieve video super-resolution. Most models use alignment or recurrent methods to directly exploit the temporal information of consecutive frames. However, the feature information extracted directly from the input frames is coarse, which affects the performance and generalization ability of the model. Thus, in this paper, we propose to investigate the role of recurrent feature updating networks. The feature update module is proposed to update and optimize the input information to improve the accuracy of features. We design the model as a multi-stage form to improve performance and generalization. Moreover, to further improve the performance of the model, we propose the difference supplement module. It allows the model to exploit the temporal differences between groups to complement the missing information in the output of each stage. Experiments demonstrate that our proposed model achieves 27.78 dB, 30.44 dB, and 39.38 dB on Vid4, SPMCS, and UDM10, respectively, which indicates that our proposed model achieves state-of-the-art performance on video super-resolution. Code is available at https://github.com/gfli123/RFUN.

show abstract